Chandrashekhar Marella

Who I Am

Senior Technology Lead focused on Generative AI and LLMOps, with a strong background in enterprise software engineering and delivery. I lead a team responsible for the production reliability of an enterprise AI (LLM) gateway — the platform through which business applications access large language models. Alongside operating that platform, I build hands-on with GenAI: RAG pipelines, agentic workflows, and Model Context Protocol (MCP) tooling. My foundation is full-stack development (.NET, MEAN / MERN) and cloud-native delivery on AWS and Azure.

My Approach

I bring enterprise engineering discipline to AI systems — reliability, guardrails, cost-awareness, and observability over hype. I favour clean, maintainable code, CI/CD, and pragmatic architecture decisions, and I care about building systems that hold up in production, not just proofs-of-concept. Having led delivery and mentored engineering teams for years, I spend as much time guiding people and design choices as writing code.

Expertise

• Generative AI & LLMOps — RAG systems, LLM orchestration (LangChain / LangGraph), model evaluation and observability (RAGAS, LangSmith / Langfuse), guardrails and PII/PHI handling; AI/LLM gateway operations (LiteLLM) — routing, rate-limiting, and cost governance.
• Agentic AI — agentic workflows and tool-calling; prototyping MCP (Model Context Protocol) tool servers.
• Cloud & Architecture — AWS (Lambda, ECS, S3, API Gateway); application and AWS architecture; API-driven services.
• Full-Stack Engineering — .NET / C#, MEAN / MERN, TypeScript, React, Node.js; SQL/NoSQL (SQL Server, MongoDB, PostgreSQL, DynamoDB) and vector databases.
• DevOps & Delivery — CI/CD (Jenkins, GitHub Actions), Docker containerization; SDLC, Agile.