Full-stack software engineer with 5+ years building scalable systems — from Angular frontends to NestJS microservices to AI-powered pipelines. Based in Tempe, AZ, currently at Deloitte.
Currently building: a local-first LLM cost and latency profiler — pip-installable, no telemetry, localhost dashboard. Pivoting into AI engineering.
Things I've built — real problems, real code.
A pip-installable Python library that benchmarks LLM providers locally — zero network calls, zero telemetry. Runs a localhost dashboard showing cost per token, p50/p95 latency, and side-by-side model comparison across Anthropic, OpenAI, and Cohere. Flagship project for my AI engineering pivot.
FastAPI + Next.js platform that scrapes, deduplicates, and scores job postings using Claude. Auto-notifies on high-match roles with APScheduler background jobs.
Paper-trading system for US equities with a holiday-aware scheduler, position sizing engine, pre-market scanner, and a live React WebSocket dashboard. Currently in 60-day paper evaluation.
More projects in the works — check back soon.
The tools I reach for and the depth I have with each.
I'm a full-stack software engineer based in Tempe, Arizona with 5+ years of experience across the entire stack — Angular and React on the frontend, NestJS and Spring Boot on the backend, PostgreSQL and MongoDB for data, and AWS for deployment.
At Deloitte I work on a microservices-based enterprise platform: NestJS services behind a GraphQL mesh gateway, centralized observability via Splunk and Datadog, and migrating legacy Struts/JSP modules to Angular + Spring Boot. Before that I was a UI developer at Nephos Technologies and a software developer at ASU's Decision Theater, where I shipped an LMS serving 500+ students.
Right now I'm pivoting into AI engineering — building tools that make LLMs production-ready: cost-aware, observable, and reliable. I'm targeting roles at companies like Stripe, Datadog, and FAANG-tier where backend craft meets AI capability. If that's your team, let's talk.
Open to AI engineering and full-stack SWE roles. Happy to chat about LLMs, microservices, or anything at the intersection of software and intelligence.