AI Enablement / Forward-Deployed Engineer — Portland, OR
I ship LLM-powered products end to end — eval harnesses, multi-agent systems, billing, deploy — and I have the operations background to make them reliable. Before software I spent 17 years running manufacturing and logistics systems (IBM, Toyota Production System): standard work, visual management, error-proofing. A system that ships predictably beats one that demos brilliantly.
Portfolio · LinkedIn · Substack · jamesyng79@gmail.com
Python · TypeScript · React / Next.js · FastAPI · PostgreSQL / SQLite · LLM evaluation & routing · multi-agent orchestration · MCP servers · Stripe · CI/CD (GitHub Actions) · Vercel / Fly.io · Azure
12+ published PyPI packages · several products with live Stripe billing · 25,000+ automated tests across the portfolio · 26,000+ downloads on the flagship tool
BenchGoblins — AI fantasy-sports decision engine. Scored LLM routing under the hood, commissioner tools, live on Fly.io + Vercel with Stripe billing.
EVE Gatekeeper — Route-intelligence platform for EVE Online: interactive 14-layer map, per-hop risk breakdown, gate-camp warnings. Stripe billing live. GitHub
anchormd — AI-agent context-file generator and auditor (CLAUDE.md / AGENTS.md). Web app + CLI + license server, Stripe billing live. pip install anchormd
Developer Tools — PyPI
| Tool | Description | Install |
|---|---|---|
| agent-lint | Workflow cost estimator and anti-pattern linter for agent YAML | pip install agentlinter |
| context-hygiene | Context-window bloat detection and signal-density scoring | pip install context-hygiene |
| promptctl | Claude API toolkit — prompt engineering, code review | pip install promptctlai |
| ai-spend | AI API cost aggregator across providers | pip install ai-spend |
| memboot | Zero-infra persistent memory for any LLM | pip install memboot |
| convergentAI | Multi-agent coordination — intent graphs, consensus voting, stigmergy | pip install convergentAI |
| mcp-manager | Manage MCP servers across agentic IDEs | pip install arete-mcp |
| arete-cc-plugin | Portable Claude Code plugin — hooks, slash commands, subagents | — |
Aurora Arcology — Investigation-board framework for narrative universes: an interactive corkboard of nodes, sourced claims, and confidence-weighted connections. Next.js 15 + TypeScript + SQLite/Drizzle, runtime-editable ontology. GitHub · Live demo
Animus — Multi-agent orchestration framework: budget controls, quality gates, checkpoint/resume, autonomous self-improvement loop. ~15k tests, 97% coverage. Docs
DOSSIER — Local-first document intelligence: ingest PDFs/emails/scans, extract entities, surface relationships, forensics timeline. Docs
Argus Overview — Linux multi-window manager for EVE Online. 26,000+ downloads. PyPI
ai-skills — Production-ready skills for Claude Code and multi-agent systems.
EVE Frontier tooling — Monolith: on-chain anomaly detector for EVE Frontier on Sui, with a live 3D-map demo of 24k systems.
TIAID — Trauma-Informed AI Deployment — a methodology for rolling out AI inside organizations without breaking the people, mapped to the NIST AI Risk Management Framework. Long-form essays on the human side of AI adoption at The Human Stack.
I scaled an ice-cream production line from 740 pints/day to 4,800/hour using Kaizen — and I bring the same discipline to software: ship, measure, error-proof, repeat. See it through. Do it better. Leave something real.