Lead AI Engineer

What You’ll Do

• Architect, build, and optimize production-grade Generative AI applications using modern frameworks such as LangChain, LlamaIndex, Semantic Kernel, or custom orchestration layers.
• Lead the design of Agentic AI frameworks (Agno, AutoGen, CrewAI etc.), enabling intelligent, goal-driven workflows with memory, reasoning, and contextual awareness.
• Develop and deploy Retrieval-Augmented Generation (RAG) systems integrating LLMs, vector databases, and real-time data pipelines.
• Design robust prompt engineering and refinement frameworks to improve reasoning quality, adaptability, and user relevance.
• Deliver high-performance backend systems using Python (FastAPI, Flask, or similar) aligned with SOLID principles, OOP, and clean architecture.
• Own the complete SDLC, including design, implementation, code reviews, testing, CI / CD, observability, and post-deployment monitoring.
• Use AI-assisted environments (e.g., Cursor, GitHub Copilot, Claude Code) to accelerate development while maintaining code quality and maintainability.
• Collaborate closely with MLOps engineers to containerize, scale, and deploy models using Docker, Kubernetes, and modern CI / CD pipelines.
• Integrate APIs from OpenAI, Anthropic, Cohere, Mistral, or open-source LLMs (Llama 3, Mixtral, etc.).
• Leverage VectorDB such as FAISS, Pinecone, Weaviate, or Chroma for semantic search, RAG, and context retrieval.
• Develop custom tools, libraries, and frameworks that improve development velocity and reliability across AI teams.
• Partner with Product, Design, and ML teams to translate conceptual AI features into scalable user-facing products.
• Provide technical mentorship and guide team members in system design, architecture reviews, and AI best practices.
• Lead POCs, internal research experiments, and innovation sprints to explore and validate emerging AI techniques.

What You Bring