Varmin Singh

About

Built and productionized enterprise LLM/RAG systems, including a Boeing internal solution that gave 400+ program managers conversational access to 1M+ rows of schedule data, with strong emphasis on governance, reliability, and reducing hallucinations in tabular domains. Also has experience running developer-focused workshops (UC Berkeley computer architecture) and partnering with customer-facing stakeholders to drive adoption of a compliance-sensitive NLP product (SEC-aligned) at Penserra.

Experience

Education

Key Strengths

• Took an internal LLM/RAG prototype to production for 400+ program managers with access to 1M+ rows of schedule data
• Built reusable ETL + schema validation to enable reliable enterprise ingestion at scale
• Improved retrieval precision and reduced hallucinations via tabular-aware chunking, metadata filters, and similarity cutoff tuning
• Implemented an evaluation loop with structured failure-case taxonomy (retrieval vs grounding vs ambiguity) to drive iterative improvements
• Diagnoses LLM workflow issues using end-to-end tracing (query → retrieved docs/scores → prompt payload → output) to isolate root cause quickly
• Enterprise integration and scalability focus (CI/CD with GitLab Runner; Redshift/Teradata; incremental indexing to avoid costly re-indexing)
• Bridges technical and customer-facing needs, translating regulatory pain points into product value and supporting adoption (SEC compliance context)