At Handshake AI, I evaluate Large Language Model responses using structured quality frameworks, prompt engineering, reasoning validation, and factual verification. I contribute to AI evaluation, annotation, benchmarking, and model improvement workflows.
At Intel Digital Readiness Program, I executed AI workflow simulations across 1,000+ records and improved workflow efficiency by approximately 20% through process analysis and pipeline optimization. I’ve also developed AI and full-stack projects, including an interview platform and a RAG-based document intelligence system.
