My background

I started as an electrical engineer working on data analysis and signal processing. From there I worked across wireless industries, from communication satellites to high-end commercial WiFi routers, constantly building hardware and software automation to characterize and test end-to-end systems.

That work led me to software, then to data science (four years productionizing forecasting models), and then to marketing, where I built an automated messaging platform and went deep on A/B testing and experimentation. Looking back, the through-line is the same: everything I've worked on has really been about separating signal from noise — in radios, in models, in metrics, and now in cities.

What I'm interested in

• How complex systems behave at the edges, not the averages
• Experimentation, causal inference, and the design of trustworthy metrics
• Practical statistics for engineers — the kind you reach for at 2 AM
• Cities as measurable systems — urban data, infrastructure, public records
• On-device and privacy-first machine learning
• Agentic orchestration and eval design
• Probabilistic programming

What I'm writing now

I'm in the middle of Measuring New York, a long-form data series analyzing NYC livability across eight dimensions — mobility, housing, environment, daily needs, public space, safety, opportunity, and time-and-stress. Every chapter is fully reproducible from a separate analysis repo.

Outside the series, I write project posts (most recently a privacy-first baby monitor running on an old Intel Mac) and opinion pieces on engineering and statistics (eight short stories about engineers using statistics, failure probability modeling).