Unico Connect Private Limited

Inside Sales Executive

Google Workspace, Inbound Deals & Deal Support

📍 Mumbai (On-site) | Full-time | 1-2 years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

We are also a certified Google Cloud Partner and an authorised Google Workspace reseller.

We are hiring an Inside Sales Executive to own the inbound Google Workspace funnel: responding to enquiries, understanding what the customer actually needs, building the deal, and taking it through to a signed subscription.

This is an inbound role. You will not be cold calling or building outbound lists.

Enquiries arrive through our website, Google referrals, and existing client relationships, and your job is to convert them.

That means a discovery conversation to size the requirement (user count, edition, term, migration needs), registering the opportunity in the Google Partner Sales Console, working with our Google partner account manager and channel team to confirm pricing and any available incentives, presenting the quote to the customer, and following through until the order is placed and the tenant is live.

The role reports to the sales lead and works alongside the technical team on setup and migration questions.

A typical day includes discovery calls with new enquiries, a pricing request to the Google partner team on an upcoming renewal, a quote sent to a customer who enquired earlier in the week, and a follow-up on a deal waiting for the customer’s approval.

Responsibilities:

Inbound Lead Qualification

Respond to inbound Google Workspace enquiries within the agreed response time.

Run the first conversation over call or video, establish the customer’s current setup, user count, timeline, and decision process, and separate genuine opportunities from information requests.

Requirement Gathering

Capture what the customer needs in enough detail to build an accurate quote: number of users, Business Starter, Standard, Plus or Enterprise edition, commitment term, data migration from Microsoft 365 or another provider, storage needs, and any compliance or security requirement that changes the edition.

Deal Creation and Pricing

Create and maintain deals in the Google Partner Sales Console.

Register opportunities, request pricing and applicable promotions or incentives, and keep deal records accurate as the conversation develops.

Coordination with Google

Work with Google partner account managers and channel relationship teams to obtain pricing approvals, clarify licensing rules, escalate blocked deals, and stay current on programme changes that affect what we can offer.

Quotation and Proposal Delivery

Prepare and send quotes and simple proposals to customers.

Explain edition differences, per-user pricing, annual against flexible plans, and renewal implications in language a non-technical buyer understands.

Deal Follow-Through and Closure

Own the deal from first conversation to order placement.

Follow up on open quotes, handle standard objections on price and edition choice, coordinate paperwork, and confirm the subscription is provisioned correctly.

Provisioning and Basic Configuration Support

Assist with tenant setup and initial configuration: domain verification, user account creation, licence assignment, and basic administrative settings.

Coordinate with the technical team on migrations and anything beyond straightforward configuration.

Renewals and Account Expansion

Track upcoming renewals across the existing Workspace customer base, initiate renewal conversations ahead of the date, and identify licence upgrades or seat additions where the customer’s usage has grown.

Pipeline Hygiene and Reporting

Maintain accurate records of every enquiry, conversation, quote, and deal stage in the CRM.

Provide a weekly view of the inbound funnel, conversion, and deals at risk.

Requirements:

1 to 2 Years of Inside Sales, Inbound Sales, or Presales Experience

In software, SaaS, cloud services, or IT products.

Candidates from a cloud reseller, Google or Microsoft partner, or IT services background will be at an advantage.

Strong Spoken and Written English

You will be the first person a prospective customer speaks to.

You must be able to hold a confident discovery conversation, write a clear quotation email, and explain a licensing decision without confusing the buyer.

Comfort with a Consultative, Question-Led Sales Conversation

Able to ask about the customer’s current environment and timeline rather than reciting product features, and able to judge when a requirement is not yet real.

Working Familiarity with Google Workspace

Gmail, Drive, Docs, Sheets, Meet, and a general understanding of the edition tiers and how organisations use them.

Deep administrative knowledge is not expected at this level.

Basic Technical Aptitude

Able to learn tenant provisioning, domain verification, licence assignment, and console navigation.

We will train you on the Partner Sales Console and the Workspace admin console.

CRM and Process Discipline

Comfortable working in a CRM, keeping deal records current, and following a defined sales process.

Reliable follow-up matters more than volume in this role.

Coordination Skills

Able to work simultaneously with the customer, our internal technical team, and the Google partner team, and to keep a deal moving when it depends on someone else.

Bachelor’s Degree

In business, marketing, commerce, technology, or a related field.

Nice to Have:

• prior work at a Google Cloud or Google Workspace reseller
• exposure to the Google Partner Sales Console or Workspace admin console
• Google Workspace Administrator or Google Cloud Digital Leader certification
• experience with Microsoft 365 to Google Workspace migrations
• familiarity with SMB and mid-market IT buying cycles in India
• 
  

To Apply

To apply, send your resume to careers @unicoconnect.com

Senior Xano Developer

Visual Backend Development, APIs & AI-Assisted Build

📍 Mumbai (On-site) | Full-time | 3-5 years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

We are hiring a Xano Developer who will build backend systems and APIs for our customer engagements on Xano, the visual backend development platform.

The mandatory requirement for this role is hands-on production backend engineering experience, including PostgreSQL data modelling and REST API design, in either a Node.js or Python environment.

Prior production work on Xano is strongly preferred.

The role is hands-on and customer-facing. You will own backend delivery across engagements: designing data models, building API flows in Xano, integrating third-party services, and partnering with frontend, mobile, and AI engineers on contracts and behaviour.

The work spans all three Xano build modes: no-code function stacks, custom code through Xano’s scripting and code blocks, and Xano’s AI assistance and agentic features.

A typical week includes a data model review for a new engagement, building a complex API flow in Xano, integrating a third-party webhook, and a customer working session on a new module.

Responsibilities:

Backend Delivery on Xano

Own end-to-end backend implementation on Xano: database schema, API endpoints, function stacks, background tasks, and integrations.

Ship production-ready work that meets customer requirements and engineering quality standards.

Build Across All Three Xano Modes

Use Xano’s no-code function stacks for standard CRUD and business logic.

Drop into custom code (JavaScript, Python through code blocks, expressions) where visual flows would be unwieldy.

Use Xano’s AI assistance and agentic features to accelerate routine build work.

Database Design on PostgreSQL

Own data model decisions for each engagement: table design, relationships, indexes, addons, and query performance.

Make schema choices that hold up as product usage grows and that map cleanly to the API contracts the client needs.

API Design and Integration

Design clean REST API contracts that the frontend, mobile, and third-party consumers can rely on.

Cover authentication, input validation, pagination, error handling, and rate limiting.

Integrate external services (payment gateways, messaging, storage, AI providers) through Xano’s connectors and custom requests.

Product Thinking and Solutioning

Translate fuzzy product asks from customers into concrete backend solutions.

Ask the right questions about edge cases, data lifecycle, multi-tenancy, and access control before building.

Push back on requirements that will cause pain later.

Customer Communication

Work directly with customers in discovery, design reviews, demos, and weekly working sessions.

Explain trade-offs in plain language, present options with clear recommendations, and write tight technical updates.

AI-Assisted Backend Development

Use Xano’s built-in AI features as well as external AI tools (Claude, Cursor, and similar) day to day for schema drafts, function stack scaffolding, query writing, integration setup, and review.

Develop strong instincts for when AI output is usable as-is and when it must be reworked.

Quality, Testing, and Reliability

Test the flows you ship.

Set up sensible error handling, logging, and alerts for the backend services you own.

Participate in incident response when something breaks in production.

Documentation and Handover

Document data models, API contracts, and non-obvious decisions inside Xano and in shared docs so the rest of the team and the customer can pick up the work without you in the room.

Continuous Learning

Track changes to the Xano platform, including new features, performance improvements, and AI capabilities.

Apply them to active engagements where they reduce build effort or improve product outcomes.

Requirements:

Hands-on Production Backend Engineering Experience (Mandatory)

Must have personally shipped backend systems to production for real users, with ownership of API design and data modelling.

POCs, coursework, and internal-only tools do not qualify.

3 to 5 Years of Professional Backend Engineering Experience

In either a Node.js or Python environment.

Candidates with slightly less time but strong demonstrated ownership are welcome to apply.

Strong PostgreSQL Skills

Schema design, indexing, query writing, and migrations on at least one production system.

Able to reason about query performance and design data models that hold up under realistic product usage.

REST API Design and Integration Depth

Comfort designing API contracts that are clean, predictable, and easy for frontend, mobile, and third-party consumers to work with.

Experience integrating external services such as payment gateways, messaging providers, storage, and AI APIs.

Familiarity with at Least One Node.js or Python Backend Stack

Such as Express, NestJS, Fastify, FastAPI, Django, or Flask.

Comfort reading and writing application code outside of visual environments when the situation calls for it.

Product Thinking and Solutioning

Ability to take a fuzzy product brief, ask the right questions, and propose a backend design that is fit for purpose.

Strong instincts for what to build first, what to defer, and what not to build.

Strong Written and Spoken English Communication

Confident in customer working sessions and design reviews.

Comfortable writing precise technical documentation and explaining trade-offs to non-engineering stakeholders.

Cloud and Deployment Fundamentals

Working knowledge of at least one of AWS, GCP, or Azure: deploying services, reading logs, managing environments, and basic operational tasks.

Familiarity with Docker is a plus.

Bachelor’s Degree

Bachelor’s degree in Computer Science, Information Technology, or a related engineering discipline.

Exceptional candidates with demonstrable production experience and strong portfolios may be considered without a formal degree.

Nice to Have

• Prior production experience on Xano, Bubble, Retool, or comparable visual or low-code backend platforms
• Full stack experience with React, Next.js, React Native, or Flutter
• Experience integrating LLM APIs (OpenAI, Anthropic, Google) into backend workflows
• Multi-tenant SaaS product experience
• Prior agency, consulting, or product-engineering experience

AI Engineer

LLMs, Agents & AI Services

📍 Mumbai (On-site) | Full-time | 2-4 years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

AI is core to how we design, deliver, and scale software for our customers.

We are hiring an AI Engineer for a dedicated client engagement building a complex production AI platform, working on the AI capabilities and agentic features at the core of the product.

The mandatory requirement for this role is at least one AI feature personally shipped to production for real users, with operational ownership.

The role suits someone who thinks quickly on solutioning, can take an ambiguous problem to a working prototype in days, and has the discipline to carry it through to production with predictable economics.

You will work alongside the Senior AI Engineer and the wider pod, with ownership of parts of the AI surface area of the product.

Responsibilities:

Solutioning and POCs

Translate ambiguous customer problems into working POCs at speed.

Pick the right model, framework, and architecture, and demonstrate value early before scaling investment.

LLM Application Development

Build AI features and services using LLM APIs from OpenAI, Anthropic, Google, and self-hosted open-weight models (Llama, Qwen, Mistral).

Choose the right model per use case based on cost, latency, capability, and context-window trade-offs.

Agentic System Design

Design and implement agentic workflows using LangGraph, CrewAI, AutoGen, LlamaIndex Agents, or custom orchestration.

Cover tool use, planning, memory, and multi-step reasoning appropriate to the problem.

API and Service Development

Build production AI services and APIs using Python and FastAPI.

Handle streaming responses, async processing, structured outputs, retries, and graceful degradation when models or tools fail.

Retrieval and Tool Integration

Implement RAG pipelines with vector databases (Pinecone, Weaviate, Qdrant, pgvector, Chroma), embeddings, chunking strategies, hybrid search, and reranking.

Integrate external tools, internal APIs, and document sources through tool-calling and MCP-style patterns.

Cost Analysis and Unit Economics

Model the per-request and per-user cost of every AI feature before it ships.

Track token usage, prompt caching, batching, and model-routing strategies.

Drive measurable improvements in unit economics.

Production Hardening

Add observability and tracing (LangSmith, Langfuse, OpenTelemetry), guardrails, content safety checks, prompt injection defences, and fallback behaviour.

Prompt Engineering and Evaluation

Design, test, and iterate prompts with measured outcomes.

Build evaluation harnesses for accuracy, hallucination, latency, and cost.

Run benchmarks across models and prompt variants before locking in a design.

Requirements:

AI Feature Shipped to Production (Mandatory)

Must have personally built and shipped at least one AI feature that runs in production for real users, with operational ownership.

POCs, internal demos, and one-off scripts do not qualify.

2 to 4 Years of Professional Software or AI Engineering Experience

With at least one production AI feature owned end to end.

Strong Python Proficiency and API Development with FastAPI

Comfort with type hints, async, packaging, testing, streaming responses, and authentication.

Production-grade Python, not notebook-only code.

Hands-on Depth Across the LLM and Agent Stack

Working experience with at least two of OpenAI, Anthropic Claude, Google Gemini, or self-hosted open-weight models (vLLM, Ollama, Together, Replicate).

Working familiarity with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or hand-rolled equivalent.

Working knowledge of RAG, embeddings, and vector databases (Pinecone, Weaviate, Qdrant, pgvector, Chroma).

Solutioning Speed and POC Velocity

Demonstrated ability to move from a fuzzy problem to a working prototype in days.

Strong instinct for what to build first, what to defer, and what to throw away.

Cost Discipline for Production AI

Ability to calculate, monitor, and optimise the cost of LLM APIs, tokens, embeddings, vector store usage, and infrastructure.

Treats unit economics as a first-class concern.

AWS Familiarity

Working knowledge of EC2, S3, IAM, and at least one of Bedrock, SageMaker, or equivalent.

Comfortable in a Fast-Moving Environment

Self-directed, comfortable with ambiguity, takes ownership without being asked, and ships under shifting priorities.

Strong Written and Spoken English Communication

Able to explain trade-offs to non-AI engineers, designers, product managers, and clients in plain language.

Nice to Have

• fine-tuning or LoRA, QLoRA, PEFT exposure
• MCP server authoring
• eval framework experience (LangSmith, Promptfoo, Ragas, DeepEval)
• open-source AI contributions
• multi-modal models (vision, audio)

Senior Backend Engineer

Node.js, System Design & Production Platforms

📍 Mumbai (On-site) | Full-time | 5+ years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

We are hiring a Senior Backend Engineer to own the backend architecture of a complex production AI platform on a dedicated client engagement: API design and data modelling, multi-tenancy, orchestration of long-running agent workloads, and the services that manage user projects and generated output.

We are open to full stack engineers whose primary strength and interest is backend. If you have shipped full stack work but the backend is where you do your deepest engineering, you are a fit for this role.

The mandatory requirement for this role is hands-on production experience as a senior backend engineer building complex, scalable systems in Node.js, with end-to-end ownership of architecture, data, and operations on at least one live platform.

The role is hands-on and architectural.

Expect to design system architecture, lead a small group of backend engineers, build the hardest parts yourself, set engineering standards, and partner closely with frontend, AI, and DevOps engineers.

A typical week includes an architecture decision on a new service, hands-on implementation of a critical path, a code review with mid-level engineers, and a working session with the AI engineer on an integration contract.

Responsibilities:

System Architecture

Own the backend architecture across engagements.

Make and document decisions on service boundaries, data models, API contracts, deployment topology, and trade-offs.

Hands-on Backend Delivery

Lead by example on complex modules, performance-critical paths, and high-risk areas using Node.js (Express, NestJS, Fastify) with TypeScript.

Pick up Python (FastAPI) where engagements require it.

Database Design and Performance

Drive PostgreSQL schema design, indexing, query optimisation, migrations, and capacity planning.

Set the data-modelling standard across the pod.

Caching, Queues, and Workflows

Design caching (Redis), event-driven patterns (Kafka, RabbitMQ, SQS, NATS), and long-running workflow orchestration (Temporal, BullMQ, Celery, or equivalent).

Handle retries, idempotency, and failure recovery.

Multi-Tenancy and Platform Patterns

Design and implement multi-tenant data isolation, RBAC, audit logging, and resource quotas appropriate to enterprise-grade products.

API and Integration Design

Set the standard for REST, GraphQL, and gRPC contracts.

Drive versioning, authentication (OAuth, JWT, SSO), security by default, and developer ergonomics.

Observability and Operations

Instrument services with OpenTelemetry, Prometheus, and Grafana.

Define SLOs, lead incident response, and write postmortems.

Code Quality and Mentorship

Run code reviews, define conventions, mentor mid-level engineers, and raise the engineering bar.

AI-Assisted Engineering Discipline

Use Claude, Cursor, and similar tools day to day.

Set the team standard for prompts, patterns, AI-assisted review, and validation of AI-generated backend code.

Client Engagement

Represent Unico Connect in technical conversations with customers.

Defend architectural decisions, communicate trade-offs, and manage scope.

Requirements:

Hands-on Production Experience as a Senior or Lead Backend Engineer in Node.js (Mandatory)

Must have personally built and shipped complex production systems in Node.js, owning architecture, data, and operations on at least one live engagement.

Full stack engineers whose deepest work is on the backend qualify.

POCs and internal tools alone do not qualify.

5+ Years of Professional Backend Engineering Experience

With at least 1 to 2 years in a senior or lead role with direct responsibility for technical decisions and team output.

Deep Node.js and TypeScript Proficiency

Strong with Express, NestJS, or Fastify.

Comfort with async patterns, streams, worker threads, and performance profiling.

Python as a Strong Plus

Hands-on production experience with FastAPI, Django, or Flask is a meaningful advantage.

Willingness and demonstrated ability to pick up Python as engagements demand is required.

PostgreSQL Depth

Schema design, normalisation, indexing, query performance, migrations, and at least one production system where you owned the data model end to end.

Caching and Event-Driven Architecture

Hands-on with Redis (or equivalent) and message queues or event-driven patterns (RabbitMQ, SQS, Kafka, NATS).

AWS Depth

Hands-on production experience with EC2, S3, RDS, IAM, VPC, ECR, and at least one of EKS, ECS, or Lambda.

Comfort owning deployment, monitoring, and cost.

System Design and End-to-End Ownership

Able to take an ambiguous problem, break it into components, evaluate alternatives, produce an architecture that holds up under review and load, plan execution, and ship with limited supervision.

AI-Assisted Engineering Experience

Daily use of Claude, Cursor, Copilot, or equivalent.

Strong discipline for reviewing and validating AI-generated backend code.

Excellent Written and Spoken English

Experience working directly with international clients.

Confident defending architectural choices in writing and in review.

Nice to Have:

• Workflow orchestration (Temporal, Airflow)
• GraphQL (Apollo, gRPC)
• Sandboxed execution environments
• Multi-tenant SaaS experience
• OpenTelemetry instrumentation
• Prior agency or consulting experience

About the Role

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies. We are hiring a Backend Engineer for a dedicated client engagement building an AI-powered application builder platform.

The backend is the operational core of the product: it manages user projects and sessions, coordinates long-running AI agent workloads, maintains project state, and serves as the integration layer between the frontend, the AI system, and the underlying infrastructure.

The mandatory requirement is hands-on production experience shipping Node.js services, with end-to-end ownership of API design, data modelling, and at least one production system involving background job processing or event-driven patterns.

Responsibilities

API and service development: Design and build REST APIs in Node.js with TypeScript. Cover authentication, session management, input validation, structured error handling, streaming responses (SSE, WebSockets), and rate limiting. Maintain clean API contracts that the frontend and AI system can rely on.

Database design and management: Own PostgreSQL schema design for product domains including user accounts, projects, file trees, session state, and generated artefacts. Write efficient queries, manage migrations, and optimise for read patterns that serve a real-time editor experience.

Caching strategy: Implement and maintain caching with Redis for session data, project state, and frequently read configuration. Design cache invalidation logic that keeps the editor experience consistent without stale reads.

Queue and background job management: Implement and operate background job infrastructure using BullMQ or equivalent. AI agent runs are long-running and stateful; handle retries, failure states, priority queues, and concurrency limits.

AI system integration: Build the integration layer between the backend and the AI agent system. Manage job dispatch, result handling, streaming output to the frontend, and error propagation.

Multi-tenancy and access control: Implement tenant data isolation, RBAC, and resource ownership enforcement across all API surfaces.

Observability and reliability: Instrument services with structured logging, metrics, and tracing. Write defensive code with sensible timeouts, fallback behaviour, and circuit breaking on external dependencies.

Testing and code quality: Write unit and integration tests for the services you ship. Review the work of peers and contribute to shared engineering conventions.

Requirements

• Hands-on production Node.js experience (mandatory) — must have personally shipped at least one feature area end to end in a production Node.js service, owning API design, data modelling, and testing.

• 3 to 5 years of professional backend engineering experience. Candidates with slightly less time but strong demonstrated ownership are welcome to apply.

• Strong Node.js and TypeScript. Production experience with Express, NestJS, or Fastify. Solid with async patterns, streaming, error handling, and building services that run reliably under sustained load.

• PostgreSQL depth. Schema design, query writing, indexing, and migrations on at least one production system.

• Redis and caching. Production experience using Redis for caching and session management. Understands cache invalidation trade-offs.

• Queue and background job systems. Hands-on with BullMQ, RabbitMQ, SQS, or equivalent. Experience managing retries, dead-letter queues, job priority, and concurrency control.

• AWS working knowledge. Comfortable with EC2, S3, RDS, SQS, and IAM. Familiar with Docker and basic deployment and environment management.

• Strong written and spoken English. Able to communicate clearly with engineers across disciplines and write precise technical documentation.

Nice to Have

Experience integrating with AI or LLM services (streaming responses, structured outputs, retry patterns); WebSocket or SSE implementation for real-time features; multi-tenant SaaS product experience; GraphQL; OpenTelemetry instrumentation; prior work on developer tools or editor-style products.

About the role:

Unico Connect is an Al-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies. We are hiring a Senior Al Engineer for a dedicated client engagement focused on building an Al-powered application builder platform - a product where users describe software in plain English and the system generates, previews, and iteratively refines working code. The mandatory requirement for this role is hands-on production experience shipping LLMpowered systems with agent architectures, with experience in code generation or developer tooling contexts a strong advantage. The role is product-focused and deeply hands-on. You will own everything between the user's prompt and correct code landing in the project: the agentic loop, code generation pipeline, context management, evaluation suite, and model cost strategy. You will work alongside the Senior MLOps Engineer who operationalises the infrastructure around your system, and collaborate closely with backend, frontend, and DevOps engineers.

Responsibilities:

Agent architecture: Design and own the agentic loop for the platform - request interpretation, planning, tool-calling sequence (read file, edit file, run build, search code, install package), and stop conditions. Make and revisit architectural decisions on singleagent vs. multi-agent designs, including planner/executor splits and dedicated buildrepair sub-agents.

Code generation pipeline: Own the end-to-end generation flow: task classification, context gathering, planning, targeted edits, verification, and commit. Implement diff/search-replace-based file editing with fuzzy matching and fallback strategies. Enforce scope discipline so the agent makes minimal diffs and does not modify code it was not asked to touch.

Self-repair loop: Build and tune the automated repair loop that pipes compiler, lint, build, and runtime errors back to the model with retry budgets and model escalation. This loop is the primary quality lever - the difference between 60-70% and 90%+ build success rates.

Context management: Build file-relevance retrieval so the agent sees the right files, not the whole codebase: dependency graphs, AST/tree-sitter-based chunking, embeddings, recency signals, and hybrid retrieval. Implement conversation summarisation and memory for long sessions, and address long-project degradation through codebase summaries and periodic consistency passes. Own token budgeting and prompt caching strategy.

Prompt engineering as a discipline: Own the system prompt and per-task prompt variants (new feature, bug fix, styling change). Maintain few-shot examples and enforce coding conventions, stack rules, and prohibited behaviours such as no hardcoded secrets and no whole-file rewrites. Version prompts like code with changelogs and rollback capability.

Evaluation and quality measurement: Design and own the evaluation suite: representative test prompts run on every prompt and model change, scored on build success rate, instruction adherence, and output quality including LLM-as-judge and visual/screenshot checks where relevant. Define regression gates that block qualitydegrading changes from shipping. Treat evals the way engineers treat automated testing: versioned, automated, and tracked over time. This responsibility is nonnegotiable at this level. 

Model strategy and cost: Design model routing - cheap and fast models for classification and small edits, frontier models for complex generation. Drive cost optimisation through prompt caching, diff-based edits over full-file rewrites, and tighter context selection. Track cost per agent run and tokens per task; evaluate new model releases against the eval suite and lead migrations when results justify it.

Safety and reliability of agent behaviour: Defend against prompt injection from user content and fetched web content. Ensure secrets never appear in generated client code. Define what the agent's tools may and may not do in collaboration with the platform team. Contribute to output moderation and abuse-pattern awareness.

Mentorship and engineering standards: Run code reviews, define engineering conventions for Al work, and raise the engineering bar across the Al team. Work closely with the Senior MLOps Engineer on handoff of eval design, prompt configurations, and model routing logic.

Requirements:

Hands-on production ownership of LLM-powered systems with agent architectures (mandatory). Must have personally shipped and operated at least one complex production Al system - agentic, multi-step, or code generation - with end-to-end ownership of architecture, evaluation, and cost. POCs, internal demos, and tutorialgrade work do not qualify.

5+ years of professional software or Al engineering experience, with at least 3 years focused on LLM applications, Al engineering, or production Al systems. Candidates with strong backend backgrounds and a clear, substantive pivot into LLM systems qualify.

Strong Python proficiency and service development. Production-grade Python with FastAPI or equivalent: type hints, async patterns, streaming responses, testing, and packaging. Not notebook-only. 

Depth across LLM APIs and agent systems. Production experience with at least two of OpenAl, Anthropic Claude, Google Gemini, or open-weight models (vLLM, Ollama, Together). Production experience with at least one agent framework (LangGraph, CrewAI, AutoGen, Llamalndex Agents) or hand-rolled equivalent. Hands-on with tool calling, structured outputs, and multi-step reasoning.

Demonstrated, systematic evaluation practice - non-negotiable. Must have built evaluation harnesses that gate production releases, not ad-hoc testing. Hands-on with at least one of LangSmith, Langfuse, Promptfoo, Ragas, or DeepEval. Candidates with no systematic answer to evaluation should not be considered at senior level regardless of other strengths.

Cost discipline for production Al. Track record of measurable cost optimisation on production Al features. Able to speak in specifics: cost per request, savings achieved through caching or model routing, context reduction decisions.

AWS working knowledge. Hands-on with EC2, S3, IAM, and Docker. Comfort with CI/CD workflows and deploying Al services.

Awareness of LLM security failure modes. Familiar with prompt injection patterns, understands that system prompt rules alone are insufficient, and has experience with output validation and content safety in production.

Nice to have: experience with AST/tree-sitter tooling, diff-based editing systems, or compiler-adjacent work; MCP server authoring; open-source Al contributions; published technical writing on LLM systems; multi-modal model experience; fine-tuning exposure (LORA, QLORA, PEFT).