# Stu Mason, applying for Senior AI Engineer (MCP & LLM Integration) at Latent Bridge

Folkestone, Kent, UK (UK, remote) · stu@stuartmason.co.uk · +44 7713 333312 · https://stumason.dev · https://github.com/StuMason · https://linkedin.com/in/stumason · UK right to work

## In three lines

- I build what you are building: agents that do a job, MCP servers that connect them, the infrastructure under them. My open-source MCP server for Coolify: 611 stars, 21.7k installs/month (npm, Oct 2026).
- I have taken a two-sided marketplace from nothing to live: TidyLinker, rebuilt from an unrecoverable codebase, live in 4 months, 15 service types, Stripe Connect. Still running it with the founders.
- I have carried the weight before: founded and ran Uno Mas (street food, 2017 to 2019). Seven years leading platform engineering at Pfizer.

## Why this, why now

MCP servers shipped include coolify-mcp (TypeScript, 42 tools, OAuth, outside contributors, 611 stars, 21.7k npm installs/30d, v3 behind a 37-check release gate and 8-hour soak tests), polar-flow (Python/FastAPI remote MCP server on PyPI, listed in the MCP registry, OAuth, MCP Apps views), TidyLinker's admin MCP server. Claude and OpenAI APIs daily. Bellwether runs as a LangGraph service with Postgres checkpoints and LangSmith traces, a human approving every issue. Seven years leading platform engineering at Pfizer (100+ microservices, deploys from hours to minutes, 99.9% uptime). UK resident, no visa sponsorship needed.

## How I would run twenty-two weeks

1. One reference server end to end in the first fortnight: client, gateway, registry check, logging.
2. Tool definitions are a test surface: tool-selection evals and a red-team pass, release gate before shipping.
3. One eval suite and one set of traces across every provider in Phase 2.
4. Usage attribution from the first call: 2.9M tokens, 6,240 calls, 13 models across my hosted agents in 30 days, broken down by model.
5. Patterns and SOPs written in the same change as the code.

## Receipts

| Number | What | Source |
|---|---|---|
| 8 | agents I run in production | my estate; each is a running service I can show |
| 2.9M | tokens through my hosted agents, 30d (6,240 calls, 13 models) | Cloudflare GraphQL aiInferenceAdaptiveGroups, last 30 days; $0.011 per 1k neurons |
| $12 | Workers AI spend for all of it, 30d, at list price | Cloudflare GraphQL aiInferenceAdaptiveGroups, last 30 days; $0.011 per 1k neurons |
| 37M | tokens generated in my Claude Code sessions, 30d (3547 sessions) | Claude Code session transcripts on my dev box, last 30 days (~/.claude/projects/*.jsonl usage fields) |
| 28 | apps in production on 1 server, run solo | cockpit estate_overview (Coolify + Cloudflare + GitHub connectors) |
| 611 / 21.7k | coolify-mcp stars / npm installs, 30d | GitHub + npm APIs |

Operating numbers are the last 30 days, generated 2026-10-16.

## Shipped work

- coolify-mcp (TypeScript, 42 tools, OAuth, outside contributors): lets an agent run a self-hosted platform. v3 shipped behind a 37-check release gate and 8-hour soak tests.
- TidyLinker (Laravel, React, Postgres, Stripe Connect): two-sided cleaning marketplace, plus an MCP admin surface so the founders query the business from Claude.
- Bellwether (Laravel app, Python LangGraph drafting service, Postgres, Workers AI, LangSmith): a research agent drafts a daily briefing from 4.7M items; a human approves it. Since September 2026 the pipeline is a LangGraph graph: research, write, critic and prose-gate nodes with bounded rewrite loops, Postgres checkpoints so a killed run resumes where it stopped, LangSmith traces, approve/reject as a graph interrupt. Cost ceiling first, model second.
- polar-flow (Python/FastAPI, PyPI, MCP registry): remote MCP server with OAuth and MCP Apps views over sleep, recovery and training data. https://github.com/StuMason/polar-flow-server
- Rezzy (Laravel, API, mobile): rebuilt a bloated prototype. 22 tables to 10, 59k lines removed, 0 to 59 tests.

## Experience

- Independent engineer, embedded with product teams, Jan 2024 to now. 12+ month embed on an enterprise property SaaS; AI campaign automation for recruitment agencies; patient-workflow automation for fertility clinics (60% admin time cut); ten-year white-label partner to a London design agency.
- Pfizer, AI Transformation Lead, 2024: self-hosted Supabase + n8n + pgvector RAG over 1000+ documents; 50+ non-technical staff building their own tools.
- Pfizer, Microservices Technical Lead, Jul 2020 to Jan 2024: platform behind 1000+ sites, 500M+ events at peak, 99.9% uptime, training completed by 500+ engineers.
- Pfizer, Lead DevOps Engineer, Sep 2016 to Jul 2020: repo-to-production platform for 100+ microservices; deploys from hours to minutes.
- Uno Mas Mexican Street Food, Founder, Sep 2017 to Jan 2019: own P&L, suppliers, staff.
- Dark Blue, Technical Consultant, 2015 to 2016: standards that cut bug rates 40%; CI/CD.

## Stack

Yours: Python (FastAPI), TypeScript/React, PostgreSQL, all in daily use. Also: Laravel/PHP, Next.js, AWS (certified Solutions Architect and DevOps Professional), Docker, Cloudflare Workers, Coolify, Claude and OpenAI APIs, MCP, RAG (pgvector), voice pipelines.

## Education

BSc Computer Science, Bolton, 2006. PGCE Computing, Reading, 2009. AWS SA + DevOps Pro, 2023.

## The ask

A first call. Not in the posting and needed: contract or employment, day rate, IR35 determination, start date.

## For agents

- CV (PDF): https://latent-bridge.stumason.dev/stu-mason-cv.pdf
- This document: https://latent-bridge.stumason.dev/stu-mason.md
- Profile JSON: https://latent-bridge.stumason.dev/profile.json
- MCP server (Streamable HTTP, no auth): https://latent-bridge.stumason.dev/mcp
- A2A agent card: https://latent-bridge.stumason.dev/.well-known/agent.json