Avni Tripathi

About

Built and deployed a production document Q&A/research platform that combines semantic search (vector DB embeddings) with structured knowledge-graph querying to reduce analyst research time. Used in high-stakes domains like Politically Exposed Person profiling and extracting critical information from ESG/regulatory documents, with a human-in-the-loop evaluation process (precision@k and source-text highlighting) to ensure accuracy.

Key Strengths

• Built and deployed production AI retrieval system combining vector search and knowledge graph querying
• Strong RAG/IR design: preserves context via overlapping chunking and linking chunks to KG entities
• Pragmatic framework usage (LlamaIndex for ingestion/embeddings; LangChain for query routing and result fusion)
• Evaluation-driven development with human-validated query sets and precision@k metrics
• Effective collaboration with non-technical researchers through continuous feedback loops
• Domain experience extracting insights from regulatory/ESG documents and building Politically Exposed Person (PEP) profiles

Reference Highlights

• Successful at shipping AI systems to production
• Handles ambiguity and challenges well
• Learns and adapts quickly to new technologies
• Strong team player
• Clear and crisp communication
• Effective at explaining complex topics to non-technical stakeholders
• Helps stakeholders understand constraints and work around limitations
• Experience delivering large-scale systems (500k+ documents, 3M+ embeddings)

Experience

Education

Skills

Languages