Suparshwa Patil

About

Built and shipped a production AI-powered Q&A/RAG onboarding assistant at One Community Global that unified knowledge across Notion, Google Docs, and Slack, cutting volunteer onboarding time by 45%. Demonstrates strong end-to-end ownership: LangChain agent orchestration integrated into a FastAPI backend, rigorous evaluation (200-query dataset, ~85% accuracy), and production feedback/monitoring with source-attributed answers to build user trust.

Key Strengths

• Built and deployed production AI QA/RAG system reducing volunteer onboarding time by 45%
• Improved system performance via caching and parallel searches (39% improvement)
• Reliability-focused evaluation approach (200-question test set; improved accuracy from ~60% to ~85%)
• Transparent AI outputs through source attribution linking answers to original documents
• Pragmatic model selection to balance quality, latency, and cost (small-model filtering before larger models)
• Designed measurable success metrics and failure-mode mapping (e.g., 85% accuracy, <2s latency)
• Continuous production evaluation with logging, user feedback loops, and automated alerts
• Effective collaboration with non-technical stakeholders; translated AI concepts into user-centric benefits

Reference Highlights

• Designed the whole backend of the system
• Provided solutions for parallel dynamicism
• Performs really great across teams and with non-technical stakeholders
• Spot-on performance in stakeholder discussions and clarifying requirements
• Fluent and clear at explaining technical concepts
• Effective at educating developers and communicating changes to stakeholders

Experience

Education

Skills

Languages

Certifications

Publications

1 publication