|
Senior software engineer with 25+ years of production experience, building agentic AI systems and the tooling around them. I run Hermes Agent by Nous Research daily as my dev environment, alongside Cursor IDE, and most of my work is in Python and TypeScript. |
- LLM agents and orchestration (LangGraph, MCP, OpenAI SDK)
- Evaluation systems that actually catch regressions (Braintrust, rubrics, failure mode analysis)
- Local model workflows and frontier model handoffs
- Boring, durable engineering practices: guardrails, code quality, life-cycle discipline
- Tools that turn "I wonder if..." into a working prototype by lunch
Started on LAMP because that's what the internet ran on. Spent years in fintech and payments, building systems where a bug means someone's money is in the wrong place. Moved into product engineering for sales and revenue organizations, where the job is turning a product vision into something the team can actually ship and iterate on. Stuck around through the JS/TS era, Cloudflare, GCP, AWS, and a lot of distributed systems.
Most of my career has been helping people go from "we have an idea" to "it's live and customers love it."
Python, TypeScript, Go, SQL, React, Next.js, Node.js, LangGraph, MCP, OpenAI SDK, Cursor, local and frontier LLMs, Braintrust, Cloudflare, Docker, AWS, GCP. Elixir-curious.
PCI DSS Level 1, SOC 2, HIPAA. I've built systems that handle payment processing, health records, and regulated data.
- LinkedIn: linkedin.com/in/tommulkins
- X: @tom_mulkins
- Tampa, FL, open to remote