Overview

Full Stack Developer (AI/ML & Web Applications)

Responsibilities

• Design and develop responsive, accessible web applications using React and Next.js with TypeScript
• Develop backend services and APIs in Python (FastAPI) and Node.js, with clear contracts (OpenAPI or GraphQL) and versioning
• Design data models and optimise queries across relational and NoSQL databases, and implement caching and background job processing
• Translate functional requirements into well-structured, maintainable and production-ready code
• Integrate LLMs in a provider-agnostic manner across commercial APIs, cloud AI platforms and self-hosted open-weight models, through an abstraction or gateway layer, so that models can be switched or compared without application changes
• Build LLM-powered features, including streaming conversational interfaces, retrieval-augmented generation with source citations, structured extraction and tool-calling agents using the Model Context Protocol (MCP)
• Implement retrieval pipelines covering document ingestion and parsing, chunking, embeddings, hybrid vector search and re-ranking
• Implement routing, caching, rate limiting and fallbacks across providers to control quality, cost and latency
• Integrate and serve pre-trained models (such as OCR, speech, classification and embedding models, including Indic language models) behind production APIs
• Fine-tune or adapt models where required (for example, LoRA fine-tuning of an LLM or embedding model), in coordination with data scientists
• Build evaluation suites for AI features (golden datasets, regression tests and LLM-based evaluation) and run them in CI as release gates
• Implement authentication and authorisation (OAuth 2.0, OpenID Connect and role-based access control), and secure handling of APIs, secrets and personal data
• Apply OWASP Top 10 and OWASP Top 10 for LLM Applications controls, including defences against prompt injection and data leakage
• Apply data-minimisation practices in compliance with applicable data protection law, including for data sent to external model providers, and design human review for consequential AI outputs
• Practise test-driven development with unit, integration and end-to-end tests, and maintain adequate coverage
• Containerise applications and manage deployments through CI/CD pipelines on Kubernetes or serverless platforms, using infrastructure as code
• Instrument applications with logging, metrics and tracing, including LLM traces, token usage and cost, and participate in incident resolution
• Ensure accessibility compliance (WCAG 2.2 and GIGW) and support for Indian languages in user interfaces
• Participate in Agile delivery, code reviews and architecture discussions
• Mentor junior developers, and document designs, APIs and operational runbooks
• Frontend: TypeScript, React, Next.js (App Router and server components), Tailwind CSS, component libraries (shadcn/ui or equivalent), TanStack Query; accessibility and internationalisation
• Backend: Python (FastAPI, Pydantic, asyncio) and Node.js (NestJS, Fastify or Express); REST with OpenAPI, GraphQL; WebSockets and server-sent events for streaming; background jobs (Celery or BullMQ)
• Databases & Caching: PostgreSQL (with pgvector), MongoDB, Redis; ORMs (SQLAlchemy, Prisma or Drizzle); schema migrations and query optimisation
• LLM Providers & Frameworks: commercial APIs (OpenAI, Anthropic, Google Gemini), cloud AI platforms (Azure AI Foundry, AWS Bedrock, Google Vertex AI), Indian providers (Sarvam, Bhashini) and self-hosted open-weight models via vLLM or Ollama; gateways such as LiteLLM; LangGraph, LlamaIndex or equivalent multi-provider frameworks; structured outputs, tool calling and MCP
• Retrieval & Vector Search: embeddings, chunking strategies, hybrid search and re-ranking; vector databases (pgvector, Qdrant, Milvus or Weaviate); document parsing (Docling or vision-language OCR models)
• Applied ML: PyTorch and Hugging Face Transformers for inference and fine-tuning (PEFT); scikit-learn; ONNX Runtime and quantised models; pre-trained models for OCR, speech (IndicConformer, Whisper) and Indic NLP (AI4Bharat)
• AI Evaluation & Observability: promptfoo, DeepEval or RAGAS in CI; MLflow; Langfuse or Arize Phoenix; OpenTelemetry, Prometheus and Grafana
• Security: OAuth 2.0, OpenID Connect, JWT, Keycloak or equivalent identity providers; OWASP Top 10 and OWASP Top 10 for LLM Applications; secrets management; guardrails for LLM inputs and outputs
• Testing, DevOps & Cloud: pytest, Vitest or Jest, Playwright; Git, GitHub Actions or GitLab CI, Docker, Kubernetes and Helm, Terraform; AWS, Azure or GCP managed services
• Data Pipelines (desirable): Airflow or Dagster; Kafka or other message queues

Qualifications

• 4+ years of professional full-stack development (5+ years preferred); minimum 2 years building and deploying AI- or ML-powered features in production applications
• Demonstrable end-to-end ownership of at least one production web application, covering frontend, backend, database, deployment and monitoring
• Demonstrable experience delivering at least one LLM or ML-powered application to end users (such as a retrieval-augmented assistant, a document-processing workflow or an agent), including its evaluation and monitoring
• Hands-on experience with Python and TypeScript in production, and with React-based frontends
• Experience deploying containerised applications on cloud platforms through CI/CD pipelines
• Experience fine-tuning or self-hosting models, working in regulated sectors, or building Indian-language applications is a plus

Education

• B.Tech./B.E., M.Tech., MCA or M.Sc. in Computer Science, Information Technology, AI/ML or a related discipline (Must have)
• Certifications are not mandatory; demonstrated work, as listed under Minimum Evidence at Screening, shall carry greater weight
• Candidates with strong verifiable work (production applications or significant open-source contributions) will be considered in lieu of formal qualification