Key Responsibilities:
- Architect and build AI-powered applications
- Design and optimize RAG systems
- Integrate and manage LLM APIs (OpenAI, Claude, open-source)
- Lead, manage, and grow the AI engineering team (2–5 engineers)
- Own task allocation, sprint planning, and technical decision-making
- Review code, enforce standards, and ensure delivery timelines
- Define AI architecture and long-term technical roadmap
- Oversee deployment on AWS / Azure
- Ensure system performance, scalability, security, and cost efficiency
Requirements:
- Strong Python expertise
- Proven hands-on RAG implementation experience
- Experience with LLM APIs
- LangChain / LlamaIndex
- Vector databases (Pinecone, Weaviate, FAISS, etc.)
- REST APIs and PostgreSQL
- Strong system design capability
- Prior experience leading technical teams