Build and deploy production-scale LLM and ML systems: own end-to-end lifecycle, optimize GPU/Kubernetes deployments, implement production APIs, monitoring, CI/CD, collaborate with product, and set AI engineering best practices.

Build and deploy production-scale AI/LLM systems: own ML lifecycle from model development to serving, optimize GPU/Kubernetes deployments, design LLM applications and APIs with monitoring, apply CI/CD and version tracking, collaborate with product teams, and contribute to AI engineering best practices.