Job Description
Experience: 3-8 Years
nLocation: Mumbai
nRESPONSIBILITIES
n
- n
- Implement RAG pipelines — document ingestion, chunking, embedding, vector store loading, retrieval and response generationn
- Build agentic workflows — LLM-driven processes with tool use, loops and error handlingn
- Integrate LLM APIs into product features — extract, classify, summarise and generate structured outputsn
- Write and maintain an LLM evaluation suite — test cases, metrics, regression trackingn
- Build FastAPI endpoints that expose AI capabilities to other services and front-endsn
- Participate in design reviews and contribute to architecture decisionsn

n

nREQUIRED SKILLS
n
- n
- Python — clean, reviewable, testable code. Not script-level, production-level.n
- LLM API usage — OpenAI, Anthropic or Azure OpenAI SDK. Streaming, function calling, token management.n




- RAG implementation — has built at least one retrieval pipeline end-to-endn
- Vector databases — has loaded and queried at least one (Pinecone, Chroma, Weaviate, pgvector)n
- FastAPI — has built and deployed at least one REST APIn
- Git and Docker — standard development workflown

n

nADDITIONAL SKILLS (increase placement level)
n
- n
- LangChain, LlamaIndex or LangGraph X— used in a real project, not documentation examplesn
- LLM evaluation — has built automated test suites, not just manual reviewn
- Agent design — can design a tool-use loop with memory and error recovery, not just implement one Fine-tuning — has fine-tuned a model (LoRA/QLoRA) and understands when to use itn

📌 AI Engineer (Mumbai)
🏢 BDO India
📍 Mumbai