Leading AI product development for hazardous waste compliance, architecting a multi-service AI platform that automates waste classification, document processing, and regulatory workflows, including a production agent for a $3B enterprise customer.

• Shipped an AI waste-classification agent for Veolia end-to-end, fine-tuning Gemini on Vertex AI and deploying on AWS, generating 20K+ structured waste profiles per month
• Designed a human-in-the-loop manifest workflow that cut document processing time 85%, combining PDF extraction, AI validation, and EPA e-Manifest automation
• Built a 7-microservice AI platform (Lambda, Fargate, Terraform) plus a portal-automation product spanning 4 disposal-facility vendors

Founded and built an enterprise AI evaluation platform from zero as solo CTO: an LLM-as-judge system that scores manager coaching sessions against a leadership competency model, backed by a multi-tenant Supabase architecture and a quantitative ROI engine.

• Designed an LLM-as-judge evaluation engine using the OpenAI Realtime API for live voice coaching sessions, with deterministic scoring and a full assessment-state lifecycle
• Architected a multi-tenant SaaS on Supabase (Postgres, row-level security, 18+ Deno edge functions) spanning coaching, billing, and reporting
• Shipped a full production stack solo: 83-test suite, CI/CD, and a React/TypeScript frontend over a serverless backend

Co-founded and led technical strategy for a multi-modal generative video platform as CTO, taking VisualLabs from Techstars '23 pre-seed funding through a production system handling 100k+ monthly render requests.

• Architected a multi-modal video generation platform on AWS, reducing render time 65% while supporting 100k+ monthly requests
• Developed proprietary fine-tuning pipelines (LoRAs, ControlNets) improving content fidelity 30%
• Established MLOps/DevOps infrastructure, cutting deployment cycles from weeks to days