AI Engineer

Role: AI Engineer

Experience: 1-3 years

Location: Mumbai or Bangalore

Work mode: Work from office

Joining: Immediate joiners preferred

About the role

Our client is a fast-growing company building an Agentic AI platform. They are looking for an AI Engineer to build and ship production LLM systems: retrieval pipelines, agentic workflows and the evaluation frameworks that keep them reliable. You will own features end to end, from data ingestion and retrieval to orchestration, evaluation and deployment.

What you will do

• Design and build RAG systems, including hybrid retrieval (dense and BM25), reranking, chunking strategies and query transformation.
• Build multi-agent and stateful workflows using LangGraph (or similar frameworks), with conditional routing, tool calling and human-in-the-loop steps.
• Develop ingestion pipelines for documents and structured sources, including OCR, metadata extraction and deduplication.
• Implement evaluation frameworks for LLM and retrieval quality (answer relevance, faithfulness, retrieval precision and recall) using tools such as DeepEval, RAGAs or Langfuse.
• Build backend services and APIs in Python (FastAPI) with async task processing, and integrate AI outputs into downstream applications.
• Work on prompt engineering and optimisation, structured outputs, model routing and fallback across providers (Claude, OpenAI, Gemini).
• Deploy and monitor systems using Docker and cloud platforms, with logging and observability.
• Use AI-assisted development tools (Claude Code, Cursor, GitHub Copilot) for implementation, refactoring, testing and code review.

What we are looking for

• 1-3 years of experience in AI/ML engineering, with at least one LLM or RAG system in production.
• Strong Python and hands-on experience with FastAPI.
• Practical experience with LangGraph or LangChain, and with vector databases such as Milvus, Pinecone or Chroma.
• Understanding of how to measure LLM output quality, not just build it.
• Working knowledge of PostgreSQL or another SQL database, Redis and REST API design.
• Familiarity with Docker and at least one cloud platform (Azure, AWS or GCP).
• B.E./B.Tech in Computer Science, AI/ML or a related field.

Good to have

• Experience with GraphRAG or knowledge graphs.
• Experience with Celery or other task queues, and with MLflow or similar experiment tracking.
• Fine-tuning experience with BERT-class or small language models.
• Exposure to voice, WebRTC or multimodal pipelines.
• Domain exposure to pharma, insurance or financial services.

What you will gain

• Ownership of production AI systems rather than prototypes.
• Work on agentic and retrieval problems at real scale.
• A collaborative, in-office engineering team.