Sri Sai Sumanth Duggina

About

AI/full-stack product engineer with experience shipping agentic systems in both fintech and enterprise compliance contexts, including an Anthropic-powered compliance Q&A tool at American Express and a home-equity assessment experience for seniors. Stands out for combining strong product instincts, typed full-stack implementation, and rigorous LLM evaluation/monitoring practices to improve trust, adoption, and operational efficiency.

Key Strengths

• end-to-end ownership of full-stack product features
• strong TypeScript and React implementation for typed forms and validation
• thoughtful backend/API design with canonical backend truth and replayability
• production monitoring and observability for agent systems
• LLM/RAG architecture design with grounding and tool use
• structured output and uncertainty-first AI design
• evaluation-driven iteration on AI quality
• improved retrieval relevance from 71% to 88% by changing chunking strategy
• shipped compliance Q&A agent to 300+ internal users in 30 days
• achieved 91% answer relevance on weekly eval sampling
• reduced manual compliance question volume after launch
• reduced user drop-off and inbound ops questions in equity assessment flow
• sound judgment on AI automation vs human-in-the-loop risk boundaries
• effective in ambiguous early-stage environments using rapid prototypes for alignment

Experience

Education

Skills

Languages

Certifications