Selected projects from RocketReach, ordered by what I'd lead with in an AI-lab platform-team interview rather than strictly chronologically. Each links to a fuller case study; deeper dives land on Writing.
Co-designed and built the in-house service that abstracts over Anthropic, OpenAI, xAI, and Gemini behind a single interface, with native websearch. Backbone for every AI feature at the company.
Solo migration of 4B+ contact records from nested JSON on a monolith model into normalized relational tables, with real-time sync, zero downtime, and zero performance regression.
Designed and built a scalable email-verification service implementing a custom async SMTP protocol, with Playwright fallback for the hardest cases. Throughput at ~500M emails/month.
Stood up the company's first data warehouse. Ran a Redshift Serverless pilot directly with the CTO and our AWS TAM, killed it for being a poor fit, launched provisioned instead. Sitemap generation went from 8 days to 4 hours.
Replaced the production ML model on the most-valuable first-party data pipeline with a rules-based model whose rules are extracted by an LLM iteratively sampling labeled data. 30× throughput, 92% cost reduction, 2.5× more usable contact data.
Rewrote in-lookup email verification to run in parallel and prioritize the right candidates first, plus a full AI domain-success tracking system. Doubled prediction success and drove lookup success from ~55% to ~90%.
Built the scalable backend AI enrichment service that became the core of the company's API enrichment product line. Hackathon prototype that turned into the multi-quarter GenAI roadmap.
Internal package that restructures and normalizes the entire phone dataset — 250M phones across 3B+ data points — into a scalable waterfall ingestion system. The PM called it "the single largest data improvement of the past year."