Srikar Yadhunandan

A Go backend for reviewing and authorizing expensive jobs before they run, with explicit state transitions, failure recovery, run diffs, and signed execution receipts.

A distributed-systems project built around exactly-once step execution, retries, saga compensation, Redis Streams, and event-backed recovery after worker crashes.

An AI engineering system for orchestrating, evaluating, and comparing LLM reasoning paths with LangGraph/LangChain, provenance tracking, retrieval, and measurable cost/quality tradeoffs.

A production-style service that exposes external data through MCP while preserving provenance, rate limits, source responses, and tamper-evident audit records.

A machine-learning evaluation harness with reproducible splits, model adapters, benchmark manifests, and analysis tools for comparing generalization across changing contexts.

A diagnostics system that combines execution traces, metrics, anomaly detection, and evidence-grounded explanations to make complex pipeline failures easier to debug.