Rutvi Rathod

About

LLM/AI backend engineer with hands-on experience taking customer LLM prototypes into production using FastAPI, containerization, CI/CD, and OpenTelemetry-based observability. Demonstrated measurable impact by cutting LLM costs ~40% and reducing workflow errors ~50% through schema-enforced outputs, better tool definitions, retries, and prompt/model optimization; also supports pre-sales via technical discovery and rapid integration demos.

Experience

Education

Key Strengths

• Took LLM prototype to production with FastAPI backend architecture (auth, caching, validation, orchestration)
• Reduced LLM costs ~40% via caching, prompt optimization, and model benchmarking
• Improved reliability/predictability with structured JSON outputs, JSON schema validation, and fallback models
• Strong real-time debugging of agentic workflows using observability (logs/traces/token usage/latency/error codes)
• Stabilized tool-using agents by clarifying tool definitions and enforcing output formats; reduced errors ~50% in a week
• Production readiness focus: containerization, CI/CD, OpenTelemetry, dashboards, retries, rate limiting, feature-flagged patches
• Effective technical demos/workshops tailored to developers with live code, debugging, and architecture walkthroughs
• Partners with sales/customer teams to translate technical capabilities into business value and close deals via targeted demos