Generative AI Engineer - LLM

COMPANIES HIRING FOR THIS ROLE :

Pixeldust | Select AI | Quantiphi | LogiNext | Excedor | Nazara

MUMBAI TECH WEEK

WHAT YOU'LL DO :

- Build LLM-powered applications including chatbots, copilots, and document intelligence tools

- Design and implement RAG pipelines using vector databases and embedding models

- Develop and optimise prompt engineering strategies and agentic workflows

- Integrate LLM APIs (OpenAI, Anthropic, Gemini, or open-source models) into products

- Build robust backend APIs to serve AI capabilities to frontend and internal systems

- Evaluate model outputs and implement guardrails for reliability and safety

- Collaborate with product teams to translate business problems into AI solutions

WHAT WE'RE LOOKING FOR :

- 2-6 years of software engineering experience with strong Python skills

- Hands-on experience building with LLM APIs or open-source models

- Solid understanding of RAG, embeddings, vector search, and prompt engineering

- Familiarity with LLM frameworks such as LangChain, LlamaIndex, or similar

- Experience with vector databases such as Pinecone, Weaviate, or pgvector

- Working knowledge of REST APIs, cloud services, and containerisation (Docker)

- Experience with fine-tuning or instruction tuning of LLMs is a plus

- Exposure to agentic frameworks or multi-agent systems is a plus

SKILLS AND TOOLS :

- Python

- LLM APIs

- RAG

- Prompt engineering

- LangChain / LlamaIndex

- Vector databases

- Embeddings

- FastAPI

- Docker

- OpenAI / Anthropic / Gemini

- Fine-tuning

- Agentic workflows