My background spans high-stakes operational environments, production software engineering, and applied ML research. Across all of them, I've learned that strong systems come from clear interfaces, disciplined validation, and good communication between people with different expertise.
About
Engineering-first AI with research credibility
I build at the intersection of forecasting research and production software, focused on reliability, deployment readiness, and working effectively across disciplines.
My senior thesis achieved up to 48% streamflow error reduction in national water forecasts using hybrid deep-learning architectures. I'm especially effective where research, engineering, and domain expertise intersect. Reliability and clarity matter as much as raw performance.
Values
What I care about
Principles that shape model design, team collaboration, and software delivery.
Reliability in Shared Systems
I design models and pipelines teammates can trust: stable metrics, leakage-safe evaluation, predictable behavior under change.
Engineering Discipline Enables Team Velocity
Clean interfaces, reproducible pipelines, and monitoring aren't overhead; they let teams move fast without breaking things.
Risk Awareness
Systems should explicitly model uncertainty and downside, not just optimize expected outcomes.
Focus Areas
Applied AI and systems engineering
Domains where I have direct implementation experience.
Time-series forecastingTransformer + RNN hybridsApplied ML for environmental systemsProduction ML and data pipelines