Lead Gen AI Engineer

We are looking for a GenAI Engineer with 4–8 years of experience to design and build scalable RAG-based and agentic AI solutions. The role involves working with vector databases, LLM orchestration, and FastAPI-based services to take AI products from prototype to production, while collaborating across ML, data, and cloud teams and mentoring engineers.

Key Responsibilities

- Design and implement scalable RAG-based GenAI systems
- Architect and optimize vector database solutions for semantic search and retrieval
- Integrate and work with MCP (Model Context Protocol) for standardized LLM tool and context management
- Build and orchestrate agentic AI workflows using LLMs
- Lead end-to-end AI solution development from prototype to production
- Develop robust APIs using FastAPI and Python. Ensuring security and scalability
- Deploy and manage AI services using Docker
- Establish best practices for code quality, version control, and CI/CD using Git
- Guide and mentor junior and senior engineers
- Collaborate with ML, data, and cloud teams to drive innovation

Must-Have Skills

- Strong hands-on experience with RAG (Retrieval-Augmented Generation)
- Expertise in Vector Databases (e.g., FAISS, Pinecone, Weaviate, Milvus)
- Experience building Agentic AI systems
- Advanced proficiency in Python

- Experience with FastAPI
- Containerization using Docker
- Version control using Git
- Solid foundation in Machine Learning / Deep Learning

Good-to-Have Skills

- Experience with Azure Cloud
- LLM fine-tuning (LoRA, PEFT, instruction tuning, etc.)
- Orchestration using Kubernetes