Hi, I'm Jim Vinson Jim Vinson,

Forward Deployed / Applied AI & AI/ML Technical Program Manager

Closing the gap between AI demos and AI production, between proofs of concept and operations at scale.

10+ years of complex program delivery at Google and Meta. $50M+ in capital programs across Google, Meta, FORTÉ, and NTT. 100+ station Starline fleet. Production AI systems built and deployed in real environments.

Open to full-time TPM, PgM, and AI Ops roles SF Bay Area/Remote
LinkedIn GitHub

Selected Work

All
Staged LLM Pipeline CEFR Database Firestore Human-in-the-Loop

PHINEAS

A staged LLM pipeline for CEFR-aligned vocabulary instruction. A word's level is data, served from a part-of-speech-aware database, so the model handles only the unknown words and the human-facing prose.

Read more
PHINEAS AI teaching assistant
Claude Managed Agent Cloudflare Workers Taste Agent Persistent Memory

Limner

The public TypeScript flagship of the Limner family: a harnessed image agent where Claude reasons and Cloudflare executes the tools in a V8 isolate, with D1 for memory. The agent gates its own output against a stylistic bar and rejects work that fails.

Read more
Limner image asset pipeline
Eval Engineering NVIDIA SkillSpector pydantic GitHub Actions

Califa Cards + Skill Foundry

A portable, versioned Skill Card standard for Claude Agent Skills. It pairs an NVIDIA SkillSpector security scan with a trigger and task-completion eval harness, keyed to a content hash so a card always describes the exact skill it was built from.

Read more
An example Skill Card rendered as a terminal-style scorecard: identity, dependencies, a color-graded quality scale, and a SkillSpector security score

Anthropic

Claude API & Claude Code

Anthropic

Primary AI provider. Multi-agent systems, RAG pipelines, code generation, and agentic development workflows.

Google

Gemini API & AI Studio

Google

Gemini models for multi-modal tasks, long-context analysis, and cross-validation in multi-agent workflows.

Cloudflare

Edge Infrastructure

Cloudflare

Workers, Pages, D1, KV - the serverless edge stack. Sub-50ms cold starts globally.

Astro

Static Site Generator

Astro

Zero-JS by default, island architecture for interactive components. Among the fastest sites on the web.

MidJourney

Image Generation

MidJourney

Concept exploration and base imagery in the original Limner: Pixel pipeline. Aesthetic control and style consistency.

Perplexity

AI Search

Perplexity

Citation-backed AI search for research and fact-checking. Direct answers with sources.

Tailwind CSS

CSS Framework

Tailwind CSS

Utility-first CSS with v4's CSS-first config. Design tokens in oklch, no PostCSS config required.

Obsidian

Knowledge Management

Obsidian

Local-first markdown PKM. Project notes, AI research, architecture decisions. No lock-in.

Asana

Project Management

Asana

Task tracking and project coordination across workstreams. Portfolio-level views for multiple concurrent projects.

Warp

Terminal

Warp

AI-native terminal with built-in command completion and workflow blocks.

Notion

Documentation & Wikis

Notion

Flexible workspace for documentation, databases, and project wikis.

GitHub

Version Control & CI/CD

GitHub

Source of truth for all projects. GitHub Actions for CI/CD pipelines to Cloudflare Pages.

Writing

All

· 5 min read

Raising Limner: Notes from a Year of Agent Husbandry

An HR consultant asked for pixel art. The discipline that came out of it turned into something I now call agent husbandry.

Silhouetted figure before towering stone architecture, pixel art in the Another World tradition

· 7 min read

Forcing Consensus: A Multi-Agent Convergence Method for LLM Evaluation

Independent LLM evaluators disagree, and averaging their scores hides the disagreement instead of resolving it. Here is a three-round method that surfaces the conflict, reconciles it through structured debate, and converges on an auditable result.

Antique desk covered in grade sheets, ledgers, and assessment documents under warm chiaroscuro lighting