Key Responsibilities
- Design and implement AI agent orchestration systems for enterprise automation
- Develop semantic intent routing and tool selection pipelines for reliable execution
- Optimize LLM workflows and structured reasoning systems for production deployment
- Collaborate with backend and frontend teams to build scalable AI infrastructure
- Implement lightweight LLM optimization techniques for latency and cost efficiency
- Architect production AI execution systems with cloud-native principles
Requirements
- Strong Python programming skills with production system experience
- Hands-on experience with LLMs and AI agent frameworks (LangGraph, LangChain)
- Knowledge of vector databases, embeddings, and semantic routing architectures
- Proficiency in FastAPI or similar backend API development
- Understanding of cloud platforms (AWS, GCP, Azure) and system design principles