Senior AI/ML engineer shipping production RAG systems, LLM orchestration, and high-throughput Python backends.
For hire · I help Chicago teams fill dev gaps in automation, data, and AI integration — when hiring full-time is too slow.
Three plain-named lanes I plug into when full-time hiring is too slow.
Pitch · I help Chicago teams fill dev gaps in automation, data, and AI integration — when hiring full-time is too slow.
Take the manual work off your team's plate.
OCR + AI extraction, document parsing, internal tools, workflow bots, scrapers, integrations. The boring repetitive stuff — done once, automated forever.
Get your data from messy to useful.
Pipelines, dashboards, cleanup, modeling, medallion architecture, vector DBs. Make decisions on numbers you actually trust.
Production AI — not demos.
RAG chatbots, agent orchestration, prompt evaluations, custom LLM workflows, MCP tooling. The AI that actually moves a business metric.
Free 15-min intro. Send the rough idea — I come back with a shape.
1-page proposal: outcome, timeline, fixed-fee or hourly. No surprises.
Async, daily updates, code in your repo from day one. NDA-friendly.
Hand-off plus two weeks of post-launch support. Docs included.
What two people say after working with me — out loud, on their own LinkedIn.
Zach treats your business outcome as the spec, not the ticket. We went from a fuzzy idea to a working tool in a few weeks — and our team has been using it every day since. I'd hire him again before I'd post a job.
Zach is who I call when something has to ship and the timeline is uncomfortable. Calm under pressure, asks the right questions early, and the work is production-grade — not a demo. Rare combination, in my experience.
Seven years of enterprise generative AI — production RAG, Python backends, and model reliability at scale.
“I write backends that think at scale. Seven years shipping enterprise generative AI at Fortune 500 firms — now building custom GenAI agents and automated infrastructure through ZL Ideation while leading production AI at Northern Trust.”
Senior AI/ML engineer with 7+ years specializing in production RAG, LLM orchestration, and Python backends at Fortune 500 financial firms.
Led the production launch of Northern Trust's first generative AI chatbot — cutting advisor document search time by 85% across 1,000+ active users.
LangGraph agent orchestration, Databricks medallion pipelines processing 10M+ records daily, LLM-as-a-judge evaluation, and Azure Function microservices under 300ms at peak load.
Because model reliability at scale is an engineering problem — and I build the frameworks that prove it before users ever see a bad answer.
Seven years, five organizations, one throughline: production AI and Python backends at scale.
A working inventory — languages, systems, and AI tooling I reach for daily.
Two artifacts: a production AI tool that won our hackathon, and a developer-first chat app.
AI-Powered Document Parsing & Generation · Salesforce
An AI-driven document automation tool that scans withdrawal and contribution forms, detects fields, tables, and checkboxes, and regenerates updated digital documents — winner of the internal hackathon.
Terminal-themed chat app built for developers
A chat application disguised as a developer's terminal — channels, code snippets, and real-time messaging wrapped in an IDE-like shell.
Certifications and a CS degree that keep the theory honest.
Bachelor of Science, Computer Science
The questions buyers usually ask in the first DM. Quick answers below.
Usually within a week. Most engagements kick off with a 1–2 week scoped pilot so you can see velocity before committing further.
Got an AI system, data pipeline, or interface waiting to be built? Let's talk.