Me
Sean Koval
I use data and AI to tackle complex problems and push toward more general, adaptive systems. In practice, that means building the full ecosystem — models, agents, tools, and evaluation — with a focus on client-facing services in finance and healthcare, where better systems can materially change outcomes.
I love building. Whether it's agents, full-stack applications, data infrastructure, or developer tools — I'm happiest when shipping something end-to-end. My projects span Python, TypeScript, and Rust, from weekend prototypes to production systems.
What I do
End-to-end from architecture and experimentation to rollout and monitoring.
Evaluation-driven pipelines with rubrics, regression tests, and human-in-the-loop review.
APIs, frontends, infrastructure — not just models. Python, TypeScript, Rust.
RAG, semantic registries, dashboards, automation — making insights usable.
Experience
Led a team of 2, architected RAG + agent features, built LLMOps evaluation pipelines, and shipped full-stack AI products.
Built real-time topic detection, analytics dashboards, and audio classification pipelines.
Built quant trading tools, data pipelines in Rust, and crypto market research systems.
Latest writing
View all →GitHub Pulse: Week of March 1, 2026
Agents learned to work in teams, SpacetimeDB collapsed the stack, and WiFi replaced cameras for human sensing.
ML Research Pulse: Week of March 1, 2026
Diffusion language models get their PyTorch moment, CUDA kernel generation outpaces compilers, and VLM efficiency breaks through with 89% token reduction.