I have spent more than eight years building software across SaaS, healthcare, education, Web3, mobile applications, internal platforms, and consumer products. My work has included founder-led product development, remote client delivery, frontend architecture, backend APIs, authentication, permissions, analytics, payment integrations, cloud deployment, and cross-platform applications.
My current focus is applied LLM engineering.
That means I am interested in the complete system around the model: how data is retrieved, how context is assembled, how outputs are evaluated, how tools and APIs are called, how failures are handled, and how the workflow becomes a product that real users can understand.
Recent work includes RAGnosis, an eight-run RAG evaluation project over a synthetic clinical database, and Pretendo, a deployed Next.js and FastAPI LLM application with model routing, validation, persistence, analytics, and provider safeguards.
I bring an unusual combination to AI teams: recent hands-on LLM application work together with years of experience shipping full-stack products in ambiguous, high-ownership environments.
I am particularly interested in senior AI full-stack, LLM application, Forward Deployed Engineer, AI product, and founding-engineer roles.
What I optimize for
- Clear product value before technical complexity
- Measurable behavior rather than impressive demos
- Typed and maintainable system boundaries
- Honest evaluation and documented limitations
- Secure handling of data and access
- Interfaces that make complex workflows understandable
- Ownership from problem definition through deployment
My current technical focus
Education and continued learning
Bachelor of Engineering in Information Science & Engineering
Applied LLM, RAG, agent-orchestration, and fine-tuning coursework
View selected certificationsOpen to the right problem