Backend Engineer

Senior AI Engineer

Code Generation, Agent Architecture & LLM Systems

📍 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 AI Engineer for a dedicated client engagement focused on building an AI-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 LLM-powered 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 single-agent vs. multi-agent designs, including planner/executor splits and dedicated build-repair 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 quality-degrading changes from shipping.

Treat evals the way engineers treat automated testing: versioned, automated, and tracked over time.

This responsibility is non-negotiable 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 AI work, and raise the engineering bar across the AI 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 AI system - agentic, multi-step, or code generation - with end-to-end ownership of architecture, evaluation, and cost.

POCs, internal demos, and tutorial-grade work do not qualify.

5+ Years of Professional Software or AI Engineering Experience

With at least 3 years focused on LLM applications, AI engineering, or production AI 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 OpenAI, Anthropic Claude, Google Gemini, or open-weight models (vLLM, Ollama, Together).

Production experience with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex 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 AI

Track record of measurable cost optimisation on production AI 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 AI 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 AI contributions
• Published technical writing on LLM systems
• Multi-modal model experience
• Fine-tuning exposure (LoRA, QLoRA, PEFT)

What we Require

We are recruiting technical experts with the following core skills and hands-on experience on

Mandatory skills : Core java, Microservices, AWS/Azure/GCP, Spring, Spring Boot

Hands on experience on : Kafka , Redis ,SQL, Docker, Kubernetes

Expert proficiency in designing both producer and consumer types of Rest services.

Expert proficiency in Unit testing and Code Quality tools.

Expert proficiency in ensuring code coverage.

Expert proficiency in understanding High-Level Design and translating that to Low-Level design

Hands-on experience working with no-SQL databases.

Experience working in an Agile development process - Scrum.

Experience working closely with engineers and software cultures.

Ability to think at a high level about product strategy and customer journeys.

Ability to produce low level design considering the paradigm that journeys will be extensible in the future and translate that into components that can be easily extended and reused.

Excellent communication skills to clearly articulate design decisions.

About Gyaan:

Gyaan empowers Go-To-Market teams to ascend to new heights in their sales performance, unlocking boundless opportunities for growth. We're passionate about helping sales teams excel beyond expectations. Our pride lies in assembling an unparalleled team and crafting a crucial solution that becomes an indispensable tool for our users. With Gyaan, sales excellence becomes an attainable reality.

About the Job:

Gyaan is seeking an experienced backend developer with expertise in Python, Django, AWS, and Redis to join our dynamic team! As a backend developer, you will be responsible for building responsive and scalable applications using Python, Django, and associated technologies.

Required Qualifications:

• 2+ years of hands-on experience programming in Python, Django
• Good understanding of CI/CD tools (Github Action, Gitlab CI) in a SaaS environment.
• Experience in building and running modern full-stack cloud applications using public cloud technologies such as AWS/
• Proficiency with at least one relational database system like MySQL, Oracle, or PostgreSQL.
• Experience with unit and integration testing.
• Effective communication skills, both written and verbal, to convey complex problems across different levels of the organization and to customers.
• Familiarity with Agile methodologies, software design lifecycle, and design patterns.
• Detail-oriented mindset to identify and rectify errors in code or product development workflow.
• Willingness to learn new technologies and concepts quickly, as the "cloud-native" field evolves rapidly.

Must Have Skills:

• Python
• Django Framework
• AWS
• Redis
• Database Management

Qualifications:

• Bachelor’s degree in Computer Science or equivalent experience.

If you are passionate about solving problems and have the required qualifications, we want to hear from you! You must be an excellent verbal and written communicator, enjoy collaborating with others, and welcome discussing a plan upfront. We offer a competitive salary, flexible work hours, and a dynamic work environment.

• 2.5+ year of experience in Development in JAVA technology.
• Strong Java Basics
• SpringBoot or Spring MVC
• Experience in AWS.
• Hands on experience on Relationl Databases (SQL query or Hibernate) + Mongo (JSON parsing)
• Proficient in REST API development
• Messaging Queue (RabitMQ or Kafka)
• Microservices
• Any Caching Mechanism
• Good at problem solving

Good to Have Skills:

• 2+ years of experience in using Java/J2EE tech stacks
• Good understanding of data structures and algorithms.
• Excellent analytical and problem solving skills.
• Ability to work in a fast paced internet start-up environment.
• Experience in technical mentorship/coaching is highly desirable.
• Understanding of AI/ML algorithms is a plus.

👋🏼We're Nagarro.

We are a Digital Product Engineering company that is scaling in a big way! We build products, services, and experiences that inspire, excite, and delight. We work at scale across all devices and digital mediums, and our people exist everywhere in the world (18000+ experts across 33 countries, to be exact). Our work culture is dynamic and non-hierarchical. We are looking for great new colleagues. That is where you come in!

Please find the job details below

Experience: 7.5-10 years

Must Have: Microservices architecture (MSA)- General Experience

 REQUIREMENTS:

• Strong technical background with node.js, event loop understanding, unit testing, developing web application & APIs, event & stream, call-back & closures, promise, async/await, accessing file system, Optimization techniques
• understanding of different components such as web server, storages, integrations
• should have worked on designing and building server-side solutions (in any technology), build process of node.js, CI/CD process of node.js, multi-tasking (working on multiple things at same time)
• Good knowledge of functional and Object-Oriented Programming
• Implementing effective security protocols, data protection measures, and storage solutions.
• Running diagnostic tests, repairing defects, and providing technical support.
• Recommending and implementing improvements to processes and technologies.
• Keeping informed of advancements in the field of Node.js development.
• Familiarity with Azure pipeline
• Should have experience in Identifying software application weaknesses and target areas and sketching out ideas for automated software test procedures. Reviewing software bug reports and highlighting problem areas.
• Knowledge of high-quality professional software engineering practices for agile software development cycle, including coding standards, code reviews, source control management, build processes, testing, and deployment.
• Fundamental knowledge of design patterns
• Experience in communicating effectively with users, other technical teams, and management to collect requirements, describe software product features, and technical designs.
• Mentoring the team members to meet the client's needs and holding them accountable for high standards of delivery.
• Being able to understand and relate technology integration scenarios and be able to apply these learnings in complex troubleshooting scenarios.

  RESPONSIBILITIES:

• Writing and reviewing great quality code
• Understanding functional requirements thoroughly and analysing the client’s needs in the context of the project
• Envisioning the overall solution for defined functional and non-functional requirements, and being able to define technologies, patterns, and frameworks to realize it.
• Determining and implementing design methodologies and tool sets
• Enabling application development by coordinating requirements, schedules, and activities.
• Being able to lead/support UAT and production roll outs.
• Creating, understanding, and validating WBS and estimated effort for given module/task, and being able to justify it.
• Addressing issues promptly, responding positively to setbacks and challenges with a mindset of continuous improvement
• Giving constructive feedback to the team members and setting clear expectations.
• Helping the team in troubleshooting and resolving of complex bugs
• Coming up with solutions to any issue that is raised during code/design review and being able to justify the decision taken.
• Carrying out POCs to make sure that suggested design/technologies meet the requirements.

Desired Candidate Profile

Java Backend Engineer - Fintech Rocketship Pilot

Distributed systems, scalability, reliability, robustness, security, quality, building responsive real time systems - do these terms get your adrenaline high? Come be a part of a high growth, fast paced engineering team building for India’s new generation.

We have an open culture, you take responsibility and ownership of what you do. No bureaucracy. No bullsh*t.

If you are up for big engineering challenges, personal and professional growth, then let’s join forces!

You’ll fit right in if you have - 2-3 years of experience building, running and maintaining production services Strong with Java and JVM based services along with PostgreSQL Comfortable working with multiple cloud providers: mainly GCP and AWS Comfortable with CI and CD tools and best practices Done TDD and values TDD

Good to have –

• Criteria : BCA / BSc/BE / BTech passouts
• Experience Required : 1 to 2 Years (Freshers Do Not Apply)
• Candidates should be ready to learn (Low-Code .NET based platform)
• Looking for immediate joiners only