I build decision systems for pricing, experimentation, and internal tooling — and the applied AI that extends them.
Eight years turning ambiguous business problems into production-grade analytics infrastructure, validation layers, and agentic workflows — at SoFi, Autodesk, ZipRecruiter, and PayPal.
Pricing compliance analytics across Personal, Student, Credit Card, and Home Loans at SoFi — OCC, Internal Audit, and 2LOD ready.
Reduction in pricing analysis cycle time through a RAG + MCP tool layer over the existing Snowflake substrate.
Pricing deployments covered by Monte Carlo anomaly detection, sustaining 99.9%+ accuracy across lending products.
Featured Case Studies
Pricing · Validation · Simulation · ToolingFrom Spreadsheet Review to Agentic Oversight: Rearchitecting Pricing Compliance at Scale.
A RAG + MCP tool layer and Monte Carlo anomaly engine that cut analysis cycle time 70%+ and sustained 99.9%+ accuracy across 1,000+ pricing deployments on a $20B+ lending portfolio.
Experimentation Guardrails: A Validation Layer for High-Stakes Pricing Launches.
A pre-launch validation framework that replaces ad-hoc, per-analyst QA with a shared check catalog — so every pricing experiment and launch ships with a structured, signed review artifact rather than a wiki page and an eyeball.
Risk Approval Simulation: Evaluating Policy Changes Before They Ship.
A simulation framework that turns proposed risk-model and policy changes into structured (population, policy, decomposition) triples — so stakeholders can compare approval, mix, and segment sensitivity before anything ships, with every assumption named as a first-class object.
Operational Intelligence: A Workflow Layer for Fragmented Pricing Deployments.
A bot + workflow layer that subscribes to events across the half-dozen systems a pricing deployment touches and reconciles them into one canonical state — so 'where is this?' and 'who owns the next step?' stop being questions that take four DMs to answer.
Applied AI Systems
Agentic · Grounded · Human-reviewedDataPilot
Turns natural-language questions over a lending portfolio into planned SQL, executed queries, and inline visualizations — compressing the analyst round-trip from half-an-hour to seconds.
ClinicalPilot
Grounds clinical reasoning over de-identified ICU EHR data in the underlying source tables and patient IDs — with guardrails that keep the system out of prescriptive territory.
MarketPulse
Stitches together Redfin and FRED data across 96 Bay Area zip codes to answer affordability, comparison, and trend questions an analyst would otherwise assemble by hand.
LifeContext
A concept system exploring how recommendation could feel if it reasoned over time-of-day, mood, and lifestyle context — not just watch history. Treated as a product-design case study in signal selection and tradeoffs.
How I Work
PhilosophySystems over one-off work.
I focus on building tools, workflows, and decision systems that make the common case easy and the complex case manageable. The goal is not just solving today's problem, but making the next ten decisions faster and better.
Design for visibility.
The best AI and analytics systems are not black boxes. I build for clarity, review, and control so people can understand what the system is doing and make better calls with it.
Trust makes speed possible.
Clear checks, reproducible logic, and a record of what changed are not overhead. They are what let teams move faster without losing confidence or taking on unnecessary risk.