I'm a principal software engineer with 20+ years building production systems. I partner with organizations that want to move past AI experiments into deployments they can actually depend on — with thoughtful architecture, proper monitoring, and a clear answer to "what happens when this breaks?"
Best fit for mid-market teams in regulated or data-sensitive industries — logistics, financial services, healthcare, legal — where running AI on your own infrastructure matters.
Getting AI into a demo is easy. Getting it to run reliably inside a real business — with production traffic, sensitive data, and real consequences when something goes wrong — is a different problem. That's the work I enjoy, and it's what I've spent my career building toward.
If you've already shipped something that's fragile or giving you pause, I can help. I'll audit what's there, walk you through the failure modes, and work with you to shore it up or rebuild where it makes sense.
Building AI into your existing systems with the same rigor you'd apply to any production service — structured outputs, validation, retries, observability. Components you can depend on, not just things that work on a good day.
Running LLMs on your own hardware so your data stays yours. Model selection, optimization, and deployment tuned to your workload. Especially valuable for teams in regulated industries or organizations with strict data privacy requirements.
Sometimes the most useful thing I can do is help you think clearly about where AI actually fits. I'll look at your infrastructure, data, and goals and give you an honest roadmap — including the places where AI isn't the right answer.
Enterprise SaaS vendors needed to know which technologies were deployed across their addressable market — roughly 515,000 organizations — and catch the leading indicator of churn: dual-vendor deployments that precede a switch. The hard part wasn't the crawler. It was a reliable, resumable, multi-stage pipeline delivering clean data to enterprise partners on a monthly SLA, against websites that break in every way imaginable.
As co-founder and CTO, I architected all of it: a Python async Playwright crawler feeding a Go signal processor (1,000+ fingerprints) into a monthly S3 delivery. The interesting piece is the account matcher — an 18-feature Random Forest at the end of a four-strategy cascade, tested at 92% accuracy while running 73% faster than v1 — and the operational spine around it: per-stage alerting, dry-run and retry-failed modes, status monitoring that let the team sleep.
A media organization needed 15,000+ videos searchable across three languages, with the AI running on their own hardware to control costs at catalog scale. I built the pipeline end to end: ingestion, whisper transcription, translation, and a three-pass LLM analysis validated against a domain-specific reference corpus.
The hard problems were the unglamorous ones: budgeting 14 parallel transcription workers into 21GB of VRAM, separating network-bound from GPU-bound work so neither starves the other, deterministic confidence scoring — rule-based, not LLM-reported — so weak analyses reach a human before publishing, and audio-only streaming extraction that cuts transfer by 90%. The receipt that it's production-grade: 5,522 translation jobs overnight, zero permanent failures.
Keyword search doesn't help when a user types "why do I keep running from what God asked me to do." Naive vector RAG doesn't either — it collapses what content is into what content speaks to. The question was how to make search actually work across 15,000+ sermons in three languages, by designing the tagger and the search layer to cooperate on purpose.
The answer is hybrid retrieval in one Postgres: a four-tier typed-embedding vector arm — weighted highest on per-phrase embeddings already pre-shaped as real user queries — fused with a lexical tsvector arm by reciprocal-rank fusion, every weight tunable from the database. Persona-based query expansion ("describe the searcher, not the solution") moves terse emotional keywords into the register of the indexed content, a small tolerant contract keeps the Python tagger and Go index from drifting, and a low-confidence signal tells the user when the system is guessing.
Every engagement starts with a written scope — nobody gets a surprise invoice, and nobody gets a surprise deliverable. Most work falls into one of four shapes:
Short-form assessment when you're not sure where to start. I look at your infrastructure, data, and goals and produce a prioritized roadmap — including honest guidance on where AI isn't the right answer. Usually the entry point to a larger engagement, but works as a standalone.
For defined builds. Paid discovery produces a written scope document; I quote a fixed price against it. Change orders handle anything outside the scope so we both stay on the same page. Typical engagements run six to twelve weeks.
For AI systems that are fragile, unreliable, or underperforming. I audit what's there, walk you through the failure modes, and work with you on a clear path forward — shore up, rebuild, or replace. The decision is yours once you have real information.
For teams with ongoing AI work who want priority access to a senior engineer. Architecture review, code review, planning help, and on-call judgment for decisions that matter. Monthly, quarterly contracts.
Twenty years of building production systems across startups and enterprise. I've led teams, architected distributed platforms, and shipped through acquisitions, migrations, and scaling moments. The AI work I do now is built on top of that foundation — not instead of it.
Based near Charlotte, NC · remote (US). Alongside consulting, I'm open to the right full-time role — details on the résumé.
I take on a small number of engagements at a time so I can give each one real attention. Whether you're looking at an ambitious project or just want a second set of eyes on something, send a note and we'll figure out if there's a fit.
I'm also open to the right full-time role — one where production AI systems, self-hosted inference, or platform architecture are the core of the work rather than a side project. Same note works.