I build projects where technical behavior is visible and testable. My strongest work sits at the intersection of machine learning, simulation-driven thinking, and software tooling that reduces friction for real users.
I care about build quality and explainability equally. A project is stronger when both code and communication are clear.
My learning style is build-first. I start from a concrete technical question, implement the smallest useful version, and then improve architecture and presentation in iterations.
That process led to a mix of repositories in symbolic regression, predictive modeling, simulation systems, and tools. The common theme is visible behavior and explainable choices.
These principles keep work practical and interview-ready instead of becoming disconnected experiments.
Models should converge, simulations should move, and tools should demonstrate utility quickly.
Use advanced methods where they matter, but keep project framing understandable and grounded.
Good engineering includes making assumptions, tradeoffs, and outcomes legible to reviewers.
Reach out through GitHub or LinkedIn. For deeper build context, my blog tracks ongoing work and implementation notes.