MD AI Engineer

Develop GenAI applications using Python, FastAPI, and LangChain to integrate LLMs like OpenAI GPT and Llama into production systems. Design and maintain RAG pipelines with vector databases such as Pinecone and pgvector, while optimizing embeddings and prompt engineering for accuracy. Build REST APIs and manage Dockerized environments using Git and Kubernetes, ensuring scalable deployment with CI/CD and observability tools. Work on agentic AI projects and function calling mechanisms to enhance autonomous workflows. Candidates must have 1–10 years of experience with a notice period of immediate to 20/30 days, reporting in a 9:30 AM to 6:30 PM shift across Bengaluru, Hyderabad, Chennai, Pune, Mumbai, Gurugram, Noida, or Delhi.