Full stack Engineer

About the Role

Shava Studios is building AI-native software products. We are hiring a Mid Senior Full-Stack Engineer to own features end-to-end across the frontend and backend, with depth in system architecture and the AI and real-time systems that connect them. We hire for demonstrated ability rather than years of experience.

Technical Environment

1. Frontend: Next.js (App Router), React, TypeScript, Tailwind CSS, MUI, Radix UI, TanStack Query, Zustand, NextAuth; Remotion for in-browser video editing and rendering.
2. Backend: Python, FastAPI, SQLAlchemy with PostgreSQL and Alembic, Pydantic; hexagonal (ports-and-adapters) microservices.
3. Async & Real-Time: Celery with RabbitMQ, Redis and Redis Streams, server-sent events, and WebSockets.
4. AI: LangGraph, deepagents, and LangChain for agent orchestration across multiple GenAI providers (OpenAI, Google, and others).
5. Tooling & Quality: Vitest, Playwright, Testing Library, pytest, Hypothesis; ruff and mypy; TDD with a strict line-and-branch coverage gate; Docker; CI on Azure Pipelines.

Responsibilities

1. Design, build, and ship full-stack features end-to-end across the UI, backend services, and async job pipelines.
2. Design and evolve service APIs, data models, and database schemas with migrations.
3. Architect and integrate LLM/agent and other AI capabilities behind clean, provider-agnostic abstractions.
4. Build and harden real-time systems (WebSockets, server-sent events, streaming) with reliable delivery and reconnection semantics.
5. Design asynchronous processing pipelines: queuing, workers, retries, idempotency, and failure recovery.
6. Manage third-party integrations (payments, AI providers, storage) behind well-defined interfaces.
7. Optimize frontend and backend performance, state management, and scalability.
8. Own security-sensitive concerns: authentication, authorization, secret handling, and secure service-to-service communication.
9. Instrument observability: logging, metrics, tracing, and structured error handling.
10. Uphold and evolve the architecture and engineering standards through technical design and code review.
11. Mentor engineers and raise the quality bar across the team.

Requirements

1. Proven full-stack delivery across a React/TypeScript frontend and a Python (or comparable) backend.
2. Sound judgment on architecture, API design, and data modeling, with the ability to articulate trade-offs.
3. Rigorous testing discipline and comfort with TDD and high coverage standards.
4. Ability to work with LLM/GenAI systems; direct experience preferred, though strong engineers eager to learn are welcome.
5. Technical leadership: thoughtful code review, clear technical writing, and a focus on root-cause fixes.

Nice to Have

1. Production experience with LLM/agent systems (LangGraph, LangChain, or similar).
2. Media or video pipelines: encoding, timeline editors, or serverless rendering.
3. Async worker systems (Celery, RabbitMQ, Redis).
4. Payments/billing and metering systems under concurrency.
5. Hexagonal architecture, ports-and-adapters, or DDD experience.

Growth

The role offers substantial influence over architecture and a clear path toward staff-level technical leadership for engineers who raise the team's standards.

Company: CombineHealth AI

Location: Bangalore, India (Work from Office — 4 days/week)

Experience: 3+ years

Employment Type: Full-time

About Combine Health

Combine Health is building an AI workforce for healthcare revenue cycle management (RCM) — agentic AI systems that automate medical coding, billing, claims, and denial management, and reason through payer policy for healthcare providers in the US. Backed by Y Combinator and Silicon Valley investors, we work with hospitals and health systems to eliminate revenue leakage and reduce manual, error-prone billing work.

We're a small, fast-moving team. Every engineer here owns real product surface area from day one — there's no hiding behind process at a 12-person company.

The Role

We're looking for a Full Stack Engineer to build and ship features across our AI-driven RCM platform — from the interfaces our customers use to review claims and denials, to the backend services that power our AI agents. You'll work closely with founders and a small engineering team, moving fast on a product that directly affects hospital cash flow.

This is not a role where requirements arrive fully specified. You'll be expected to help define what to build, not just how.

What You'll Do

• Design, build, and ship full stack features across the product — from UI to APIs to data models
• Build interfaces for complex, data-heavy workflows (claims review, denial queues, coding dashboards) that need to be fast and legible, not just functional
• Work with backend services that integrate with AI agents, payer systems, and healthcare data sources
• Own features end-to-end: design, implementation, testing, deployment, and iteration based on customer feedback
• Collaborate directly with founders and product on prioritization — this isn't a "tickets handed to you" role
• Write clean, maintainable code and help set engineering practices as the team scales
• Debug and resolve production issues quickly in a live, customer-facing system

What We're Looking For

• 3+ years of professional experience building full stack web applications in production
• Strong hands-on experience with a modern frontend framework (React or similar) and backend framework/language (Python, Node.js or similar)
• Comfort working across the stack: REST/GraphQL APIs, relational databases (Postgres/MySQL), and basic infra/deployment (Docker, cloud platforms like AWS/GCP)
• Ability to take a loosely defined problem and ship a working solution without waiting for a detailed spec
• Solid fundamentals in data modeling, system design, and debugging complex issues in production
• Startup mindset: comfortable with ambiguity, fast iteration, and wearing multiple hats
• Strong communication — you'll be working directly with a small team and need to explain trade-offs clearly

Good to have:

• Experience integrating with AI/LLM APIs or building AI-adjacent product features
• Prior experience at an early-stage startup (seed to Series A)

Why Join Combine Health

• Work on a product with real, measurable impact — faster payments, fewer denials, less manual work for healthcare teams
• Small team, high ownership — your work ships and matters immediately
• Backed by Y Combinator and top investors, early enough that your decisions shape the product
• Direct access to founders and fast decision-making, no layers of bureaucracy

How to apply

• Please click on the link and fill in the details: https://forms.gle/8tX3sXpFZQKotB9e9 

To apply, share your resume along with links to relevant projects or GitHub/portfolio.

Full-Stack Engineer (Backend Heavy)

Experience: 4–6 Years | Function: Engineering — Product | Location: On-site

About Us

We’re building the next generation of AI-powered business software, and we’re looking for people who want to shape that future with us. With Lumen, we’re reimagining how users interact with CRM — moving beyond screens, menus and dashboards to an intelligent interface where users can simply ask AI to take actions, retrieve knowledge, generate insights and get work done. With Agent Studio, we’re enabling businesses to build, test and deploy their own AI agents for real-world workflows. And with Invorto, we’re bringing AI to voice, allowing businesses to create intelligent voice agents tailored to their customer and operational use cases.

What makes this especially exciting is the stage and scale of the opportunity. You’ll get to work on genuinely hard problems across LLMs, agents, reasoning, orchestration, voice AI, evaluation, reliability and enterprise security — not as isolated experiments, but as products used in real business workflows. You’ll have the opportunity to build zero-to-one, own meaningful parts of the product end-to-end, work closely with customers, experiment rapidly, and see your work reach production at scale.

Why join now? Because the playbook for enterprise AI is still being written. You won’t just be implementing someone else’s roadmap — you’ll help define the product, architecture and experiences that become that playbook. Expect high ownership, fast iteration, hard technical and product problems, direct customer impact, and the chance to build AI systems that have to work reliably in the real world — not just in a demo.

About the Role

We are looking for a Full-Stack Engineer with a strong backend bias to help build end-to-end product experiences across Lumen and Agent Studio. You will own features from database and API design through to the front-end experience, working closely with product and design to ship AI-powered experiences that real business users depend on every day.

What You’ll Do

Design and build backend services and APIs in Python that power core product and AI-agent features.

Build front-end interfaces and experiences that let users interact naturally with AI agents, insights and CRM workflows.

Own features end-to-end — from data modeling and backend logic to UI implementation, testing and release.

Work with product managers and designers to translate requirements into well-architected, scalable systems.

Integrate with LLM-based and agentic backend systems built by the AI/ML engineering team.

Optimize application performance, reliability and code quality across the stack.

Engage directly with customers and customer success teams to understand workflows, triage issues and inform roadmap decisions.

What We’re Looking For

4–6 years of professional full-stack engineering experience, with a clear backend-heavy skill set in Python.

Strong experience designing and building REST/GraphQL APIs, data models and scalable backend services.

Working proficiency with modern front-end frameworks (e.g., React) to build and integrate user-facing features.

Experience with relational/NoSQL databases, caching and cloud infrastructure.

Ability to move fast in a zero-to-one environment while maintaining code quality and system reliability.

Strong communication skills — this is a customer-facing role, and you will be expected to clearly articulate technical concepts, decisions and trade-offs to both technical and non-technical stakeholders, including customers.

Good to Have

Experience building features on top of LLM or AI-agent backends.

Prior experience in CRM, SaaS or enterprise business applications.

Exposure to real-time or voice-based product interfaces.

Full Stack Developer

Experience: 3 to 5 Years

Location: Hyderabad

Interview Mode: Face-to-Face (F2F)

Work Mode: Hybrid

Employment Type: Full-Time

Note: Immediate joiners or candidates with a notice period of up to 15 days are preferred. We are only considering candidates who can attend a face-to-face interview at our office.

Role Summary;

We are looking for a Full Stack Developer (React.js + Python + AWS + AI) to design, develop, and maintain scalable web applications and AI-powered solutions. The ideal candidate must have strong experience in React.js, Python, AWS, and AI development. Hands-on AI development experience is mandatory for this role.

Mandatory AI Skill Requirement - AI development experience is mandatory. Candidates without hands-on AI development experience will not be considered.

Candidates must have practical experience in one or more of the following:

• Building AI-powered applications.
• Working with Large Language Models (LLMs).
• Prompt Engineering.
• Retrieval-Augmented Generation (RAG).
• AI agent development using LangChain, LangGraph, or similar frameworks.
• Integrating AI models through APIs such as OpenAI, Anthropic, or Gemini.
• Developing AI-enabled workflows and intelligent business applications.

Note: Experience using AI coding assistants (ChatGPT, GitHub Copilot, Claude, Gemini, etc.) alone does not meet this requirement. Candidates must have actual AI application development experience.

Key Responsibilities

• Develop and maintain full-stack web applications.
• Build responsive frontend applications using React.js.
• Develop backend REST APIs using Python (FastAPI / Django / Flask).
• Design, develop, and integrate AI-powered features into applications.
• Develop and deploy applications on AWS cloud services.
• Work with relational databases (MySQL / PostgreSQL / SQL Server).
• Integrate frontend and backend components.
• Follow Agile/Scrum development processes.
• Write clean, maintainable, and production-ready code.
• Collaborate with cross-functional teams to deliver scalable and high-quality solutions.

Required Skills (Mandatory)

• 3 to 5 years of Full Stack development experience.
• Strong experience in React.js.
• Strong backend development experience in Python.
• Hands-on experience with AWS cloud services.
• Hands-on AI development experience (Mandatory).
• Experience with LLMs, Prompt Engineering, RAG, LangChain, LangGraph, or similar AI frameworks.
• REST API development experience.
• Strong SQL database experience.
• Git and Agile development workflow.
• Good understanding of software design principles and best practices.

Good to Have

• Docker
• CI/CD pipelines
• Microservices architecture
• Kubernetes
• Experience with vector databases and AI model integrations

Preferred Qualifications

• Bachelor's degree in Computer Science or a related field.
• Strong problem-solving and analytical skills.
• Good communication and teamwork abilities.
• Passion for learning new technologies, especially AI, cloud technologies, and modern software development.

About the Role

We are looking for a hands-on Applied AI / Full Stack Engineer to build AI-powered products and experiences. The ideal candidate should be comfortable working across AI, backend, and frontend and taking features from idea to production.

Key Responsibilities

• Build and deploy AI/LLM-powered applications and features.
• Develop AI agents, RAG pipelines, tool/function-calling workflows and integrations.
• Build scalable backend APIs and services.
• Develop frontend applications using React/Next.js.
• Integrate LLMs such as OpenAI, Claude, Gemini, etc.
• Work with databases, cloud platforms and production deployments.
• Collaborate with product and design teams and take ownership of features end-to-end.

Must-Have Skills

• 3–6 years of software engineering experience.
• Strong Python and/or TypeScript/Node.js.
• Strong React.js / Next.js / TypeScript experience.
• Hands-on experience with LLMs / Generative AI.
• Experience with RAG, AI Agents or tool/function calling.
• Experience building and deploying real-world products.
• Good understanding of APIs, databases and cloud deployment.

Good to Have

• LangChain / LangGraph / LlamaIndex
• PostgreSQL / Vector Databases
• AWS / GCP / Azure / Vercel
• Docker / CI/CD
• Experience in an early-stage startup or AI product company.

We are looking for builders who can take a problem, experiment, build, ship and improve it—not just candidates with AI keywords on their resume.

Apply: https://processity.ai/careers/fullstack-ai-engineer

BigMantra is a Vertical Autonomous AI Agent Builder — we build AI companies that go a mile deep into specific industries. Our products include Mantra Spaces (AI-powered UK HMO property management) and Verity Law (AI-powered legal conveyancing). Our team is small, our stack is modern, and your code ships to production the same week you write it.

We're looking for a Fullstack AI Applied Engineer who can build full applications end-to-end and wire AI agents into production systems that real users depend on.

WHAT YOU'LL DO

• Build and ship full-stack web applications using React / Next.js and Python / Node.js

• Design and implement AI agent workflows using LangChain, LangGraph, Claude Agent SDK, Agno, or similar

• Integrate agents with real-world APIs — Salesforce, Google Workspace, WhatsApp Business, email providers

• Build and optimize database layers — production SQL, schema design, RAG pipelines

• Own deployment and infrastructure — Docker services, CI/CD pipelines on AWS or Azure

• Write tests that matter — E2E, load tests, performance benchmarks

• Collaborate directly with the founding team on architecture and product direction

MUST HAVE

• 3+ years of professional software engineering experience

• Strong JavaScript / TypeScript — React, Next.js, Node.js in production

• Strong Python — backends, agent systems, data pipelines

• Hands-on experience with at least one AI agent framework (LangChain, LangGraph, Claude Agent SDK, Agno, or equivalent)

• Docker services for containerization and deployment

• CI/CD pipelines — GitHub Actions, GitLab CI, or similar

• Deployment experience on AWS or Azure

• Solid SQL and database skills — schema design, query optimization

GOOD TO HAVE

• Experience with autonomous agents — MCP (Model Context Protocol), skills, plugins, tool-use

• Memory and context management for long-running agents

• Prompt engineering and optimization

COMPENSATION & BENEFITS

• ₹30L – 50L per annum (based on experience)

• Equity / ESOPs — early-stage participation

• Remote-friendly — Coimbatore office available

• Learning budget — courses, conferences, AI tooling subscriptions

• Flexible hours — output over seat time

We are seeking a Senior Full Stack Engineer to join our team in a long-term contractor capacity to continue development of a production-grade platform hosted on AWS.

This application supports policy processing, third-party integrations, compliance workflows, reporting, and intelligent automation capabilities. The ideal candidate is a strong software engineer first, capable of contributing across the full stack while helping scale and evolve the platform.

This role requires someone who can step into an existing system, understand complex workflows quickly, and independently deliver high-quality solutions.

Responsibilities

• Design, develop, and maintain full-stack application features across frontend and backend systems

• Build and support integrations with third-party systems and APIs

• Develop workflow-driven processes using Temporal

• Build scalable APIs and backend services using Python

• Maintain and optimize relational databases using PostgreSQL

• Develop reporting and analytics capabilities using charting libraries

• Contribute to AI-enabled features and integrations within the platform

• Improve CI/CD pipelines and deployment processes

• Participate in architecture discussions and help shape long-term technical direction

• Work closely with business and technical stakeholders to deliver production-ready solutions

Required Qualifications

Engineering

• at least 7+ years of full stack software engineering experience

• Strong proficiency in Python

• Strong frontend development experience with modern web frameworks

• Strong backend API development experience

• Experience designing and building scalable applications

• Strong understanding of software architecture and best practices

• Experience working in complex, integrated systems

Workflow and Orchestration

• Proven experience with Temporal

• Experience building and managing workflow orchestration patterns

• Familiarity with asynchronous processing and event-driven systems

Database and Reporting

• Strong experience with PostgreSQL

• Strong SQL and data modeling experience

• Experience building reporting dashboards and analytics features

• Experience with charting libraries such as Chart.js, D3.js, or Plotly

DevOps

• Experience with CI/CD pipelines

• Familiarity with containerized deployments

• Experience with cloud environments and modern development workflows

Preferred Qualifications

• Experience in insurance, surplus lines, or compliance-based applications

• Experience integrating with third-party vendors and external APIs

• Experience with AI tooling, LLM integrations, and context engineering

• Experience building intelligent automation features

What We Are Looking For

• Self-driven and highly autonomous

• Strong problem-solving ability

• Comfortable with ownership and accountability

• Able to contribute with minimal supervision

• Strong communication skills in English

• Comfortable working U.S.-based business hours

Ideal Candidate

A senior full stack engineer who can quickly contribute to an active production system, own features end-to-end, and help expand a platform that sits at the center of complex business workflows and integrations. Send resume with projects and contact information.

Job Title

Python Full Stack Developer – AI

Experience: 6-9 Years

Location: Bangalore (Hybrid)

Employment Type: Full-Time

Job Summary

We are seeking a highly skilled Python Full Stack Developer with AI expertise to design, develop, and deploy scalable AI-powered applications. The ideal candidate should have strong experience in Python, Full Stack Development, REST APIs, modern frontend frameworks, and Generative AI technologies, including LLMs, prompt engineering, and AI integrations.

The role involves building end-to-end web applications, integrating AI models, and collaborating with cross-functional teams to deliver innovative AI-driven solutions.

Key Responsibilities

· Design, develop, and maintain scalable full-stack applications using Python.

· Build responsive and interactive user interfaces using React.js, Angular, or Vue.js.

· Develop backend services and RESTful APIs using Django, Flask, or FastAPI.

· Integrate Generative AI models such as OpenAI GPT, Claude, Gemini, or Llama into business applications.

· Develop AI-powered chatbots, assistants, document processing, and workflow automation solutions.

· Implement prompt engineering techniques to optimize AI model performance.

· Build Retrieval-Augmented Generation (RAG) pipelines using vector databases.

· Work with LangChain, LangGraph, or LlamaIndex for LLM orchestration.

· Integrate AI APIs and third-party services into enterprise applications.

· Design and optimize SQL and NoSQL databases.

· Deploy applications on AWS, Azure, or GCP.

· Develop CI/CD pipelines and manage deployments using Docker and Kubernetes.

· Write clean, reusable, and well-documented code following best practices.

· Participate in Agile ceremonies, code reviews, and sprint planning.

Required Technical Skills

Backend

· Python

· Django

· Flask

· FastAPI

Frontend

· React.js / Angular / Vue.js

· HTML5

· CSS3

· JavaScript (ES6+)

· TypeScript

AI / Generative AI

· OpenAI API

· Azure OpenAI

· Gemini API

· Claude API

· Llama Models

· LangChain

Databases

· PostgreSQL

· MySQL

· MongoDB

· Redis

Cloud & DevOps

· AWS / Azure / Google Cloud Platform

· Docker

· Kubernetes

· Git

· GitHub

· Jenkins

· CI/CD

API Development

· REST APIs

· GraphQL (Preferred)

· API Integration

Preferred Skills

· Machine Learning fundamentals

· NLP (Natural Language Processing)

· Hugging Face Transformers

· TensorFlow or PyTorch

· Kafka or RabbitMQ

· Elasticsearch

· Microservices Architecture

· Authentication (OAuth2, JWT)

Qualifications

· Bachelor's or Master's degree in Computer Science, Information Technology, or a related field.

· 6–9 years of experience in Python Full Stack Development.

· Hands-on experience with Generative AI and LLM-based application development.

· Experience working in Agile/Scrum environments. 

Job Title : Senior Consultant – Full Stack Developer with AI

Experience : 5+ Years

Open Positions : 1

Location : Remote

Working Hours : 11:00 AM to 08:00 PM IST

Engagement : 6 to 8 Months Contract-to-Hire (C2H), with potential conversion to client payroll

Expected Joining : By the last week of August / 1st week of September

Role Overview :

Thoughtworks is looking for a Senior Consultant – Full Stack Developer with AI experience who can design and develop scalable full-stack applications while leveraging modern AI development tools and agentic AI capabilities.

The ideal candidate should have strong hands-on experience with Python, JavaScript / React.js, AWS Bedrock Agent Core, Docker, Kubernetes, and modern AI-assisted development frameworks and tools. Experience building MCP servers / tools, AI skills, or integrations using tools such as Cursor, Claude Code, Codex, or GitHub Copilot will be highly valuable.

The candidate should be comfortable working across application development, AI integration, cloud technologies, and containerized environments.

Mandatory Skills :

Python, React.js / JavaScript, AWS Bedrock Agent Core, Docker, Kubernetes, MCP / AI Skills, Cursor / Claude Code / Codex / GitHub Copilot, Full-Stack Development.

Key Responsibilities :

• Design, develop, and maintain scalable full-stack applications using modern development practices.
• Build backend services and APIs using Python and related frameworks.
• Develop responsive and scalable frontend applications using ReactJS or other JavaScript frameworks.
• Design and implement AI-powered solutions using AWS Bedrock Agent Core.
• Build and integrate AI agents, tools, skills, and workflows into enterprise applications.
• Develop and work with MCP (Model Context Protocol) servers, tools, or integrations.
• Leverage AI-assisted development platforms and coding tools such as Cursor, Claude Code, Codex, or GitHub Copilot.
• Containerize applications and services using Docker.
• Deploy, manage, and troubleshoot containerized workloads using Kubernetes.
• Collaborate with cross-functional teams to understand business requirements and translate them into scalable technical solutions.
• Follow engineering best practices around code quality, testing, security, performance, and maintainability.
• Contribute to CI/CD and cloud deployment processes; DevOps experience will be an added advantage.
• Participate in technical discussions, architecture decisions, code reviews, and project delivery.

Mandatory Skills :

• 5+ years of relevant software development experience.
• Strong hands-on experience with Python.
• Strong experience with ReactJS or another modern JavaScript framework.
• Hands-on experience with AWS Bedrock Agent Core.
• Strong experience with Docker.
• Hands-on experience with Kubernetes.
• Experience building MCP servers / tools, AI skills, or similar AI integrations.
• Experience using AI-assisted coding/development tools such as :
• Cursor
• Claude Code
• Codex
• GitHub Copilot
• Strong understanding of full-stack application development.
• Good understanding of API development, application architecture, and cloud-based solutions.

Nice to Have :

• Experience with DevOps practices and CI/CD pipelines.
• Experience with AWS cloud services beyond Bedrock.
• Experience with infrastructure automation and deployment.
• Experience building production-grade GenAI / Agentic AI applications.
• Experience with LLM integrations, AI agents, tools, and function calling.

Project Expectations :

Candidates should be able to explain at least one recent project in detail, including :

• Problem Statement : What business / technical problem were you solving ?
• Architecture & Approach : How did you design the solution ?
• Key Contributions : What did you personally build or own ?
• AI / Agent Implementation : How did you use AWS Bedrock Agent Core, MCP, or AI development tools ?
• Technology Stack : Python, React.js / JavaScript, AWS, Docker, Kubernetes, etc.
• Challenges : What were the major technical challenges ?
• Outcomes & Metrics : What measurable impact did the solution deliver, such as performance improvement, cost reduction, automation, productivity improvement, or reduced development time ?

Interview Process :

1. Round 1 – GT Technical Interview : 60 minutes
2. Round 2 – Client Technical Interview : 60 minutes
3. Round 3 – Project Round : 60 minutes
4. Additional Client Round : May be conducted on a case-by-case basis

Key Hiring Priorities :

Highest priority : Candidates with genuine hands-on experience in AWS Bedrock Agent Core + Python + React / JavaScript + Docker + Kubernetes + MCP / AI skills and practical experience using modern AI coding/agent development tools.

Note : Candidates should demonstrate hands-on implementation experience rather than only theoretical knowledge or exposure to the above technologies.

Job Title: Full Stack AI Engineer

Location: Remote/Hyderabad

Experience Level: 3-5

Salary Range: 12-18LPA

Application Link:https://beyond.ciltriq.com/apply/BUILD

Description:

Join a team building AI-powered systems that solve complex business problems and automate operational workflows across document processing, voice agents, enterprise integrations, workflow automation, and multi-agent systems.

Strong full-stack foundations: frontend state management, asynchronous user experiences and performance; backend API design, authentication, data modelling, databases, queues and distributed systems.

Strong coding ability in Python and JavaScript or TypeScript, with practical experience in modern frontend frameworks and backend services.

Requirements:

- Design and build complete systems: frontend applications, backend services, APIs, databases, data pipelines and integrations with customer systems.

- Build multi-agent workflows with clear agent responsibilities, tool access, shared state, context management, routing, handoffs and coordination across sequential and parallel tasks.

- Make agent execution dependable through durable state, checkpoints, retries, timeouts, idempotency, recovery and human approval or review where needed.

- Deliver document-processing pipelines, voice agents and retrieval-based AI applications, connecting model outputs to useful actions in real business workflows.

- Own quality in production: automated tests, AI evaluations, guardrails, observability, access controls, deployments, incident response and clear documentation.

- Choose where AI adds value and where deterministic software is the better fit. Balance accuracy, latency, cost, security and maintainability.

- Improve reusable engineering foundations, review code and help other engineers grow as the team expands.

- A solid understanding of tool calling, structured outputs, retrieval, context and memory management, model selection and evaluation.

- Practical cloud and deployment experience, including containers, CI/CD, secrets management, logging, monitoring and production debugging.

- Ability to reason from first principles, investigate failures across system boundaries and communicate technical decisions clearly to customers and teammates.

- Useful additional experience: Document AI and OCR, real-time voice systems, enterprise integrations, agent protocols such as MCP, and orchestration frameworks.

- Useful additional experience: Mentoring engineers or building reusable platforms.