skip to content
Currently · at ATA LLC

Daniel Raymond

Senior AI Engineer · Director-track builder
Remote · United States · 15+ yrs
◆ theducklabs · 2026 / field notes from a builder

I architect production-grade AI & the teams that ship it.

Fifteen-plus years across LLM systems, agentic AI, DevSecOps, and cloud. Currently leading enterprise AI at ATA LLC — before that, running my own consultancy and leading DevSecOps on a $500M defense program at Lockheed Martin.



02 How I Think · Operating Principles four rules, hard-won
Prototype fast. Production deliberately.
— signed, every AI platform I've built

Architect for what comes after the demo.

Retrieval, orchestration, evaluation, infrastructure, security, approvals — the work that lets teams actually depend on the system.

Autonomy with kill switches.

Governance, auditability, and human approval where they matter — useful agents in real organizations, not lab toys.

Measurable behavior over vibes.

Regression checks, eval harnesses, observable workflows. If you can't measure it, you don't really ship it.

Local-first when it matters.

I work fluently across hosted APIs and self-hosted stacks — privacy, latency, and cost decide which one.

read the full operating manual →

03 The Stack · What I Actually Ship With not just experiment with

Tools I've put into real production — across hosted and self-hosted.

Frontier assistants where they earn their cost. Local runtimes where privacy or latency demands it. Glue that ages well.

Codex ChatGPT Claude Gemini Ollama vLLM Hermes Diffusers LangGraph FastAPI pgvector WebSockets Codex ChatGPT Claude Gemini Ollama vLLM Hermes Diffusers LangGraph FastAPI pgvector WebSockets
RAG Agent workflows Structured extraction Eval harnesses Python TypeScript Terraform Kubernetes AWS CI/CD DevSecOps SQLite RAG Agent workflows Structured extraction Eval harnesses Python TypeScript Terraform Kubernetes AWS CI/CD DevSecOps SQLite
04 Let's Build · Direct Line

Got a hard AI problem?

Production architecture. Agent platforms. Governance and evals. Build-vs-buy. I read every inbound — usually reply within a day.