I build AI systems that
hold up in production.

Veridia — explore the world.

A playable open-world demo built entirely in vanilla JS + WebGL — no engine, no framework. WASD to walk, visit all five gates to read the story, and rest by the tavern. Deployed on Cloudflare Pages.

• ›Build and validate Python backend connectors that replicate SaaS tools and workflows for AI-agent training and evaluation.
• ›Create and verify realistic agent tasks and workflows, assessing correctness, realism, and task quality through structured QA and evaluation rubrics.
• ›Contribute to infrastructure and training data used to develop and evaluate AI agents, including failure analysis and repeatable quality checks.

• ›Shipped production full-stack apps (React.js, Django REST, FastAPI); improved API response times 35%.
• ›Built accessible Tailwind UIs with OAuth-secured APIs across concurrent client projects.
• ›Owned features end-to-end — schema design, REST endpoints, UI — across multiple client codebases in parallel.

• ›Built FastAPI inference endpoints handling 150 concurrent req/s.
• ›Integrated PostgreSQL pipelines for AI-output storage/monitoring; optimized model-serving latency.
• ›Load-tested and profiled serving paths to keep p95 latency stable under concurrent inference traffic.

• ›Built NL2SQL models; A/B tests improved multilingual transcription accuracy to 76%.
• ›Automated workflows with LangChain agentic pipelines.
• ›Ran structured A/B evaluations across model variants to pick production candidates on accuracy-per-cost.