Lokeshwar Kodipunjula

About

LLM/ML platform engineer with hands-on experience taking an LLM document summarization prototype into a production-grade service on AWS EKS, emphasizing low-latency inference, drift monitoring, and safe CI/CD rollouts (canary + rollback). Strong in real-time debugging of agentic/RAG systems (tracing, retrieval/index drift fixes) and in developer enablement through practical workshops (Docker/Kubernetes/FastAPI) plus pre-sales support via demos and benchmarks to close pilots.

Experience

Education

Key Strengths

• Took an LLM prototype (document summarization) to production on AWS EKS with CI/CD and safe rollout practices
• Performance and reliability optimization (batching, inference optimization, autoscaling) to address latency
• Production ML quality management (drift detection via fixed eval set + monitoring)
• Risk-managed deployments (model versioning, canary rollouts, automatic rollback)
• Real-time troubleshooting of agentic/RAG workflows using tracing and log-driven root cause analysis
• Rapid incident recovery during live demos (identified retrieval index drift, rebuilt index, tightened filters, added validation fallback model)
• Strong developer-facing communication (hands-on demos/workshops with real code and live debugging)
• Effective pre-sales partnership (prototypes, benchmarks, deployment plans to de-risk and close pilots)