Phil Springer · Senior AI Platform Engineer
Phoenix · Open to roles

Senior AI Platform Engineer

I use AI-assisted engineering to build infrastructure and tooling: an agent harness, release gates, MCP server vetting and model routing. My AI work uses planted-bug tests, review by a model from another lab and human approval for sending, spending and deletion.

Human approval gates

Sending, spending and deletion require my recorded approval.

How I ship

Release evaluation

One recent gate passed 35 of 35 tests and caught all 13 bugs we planted before it went live.

How I evaluate releases

toolwitness.ai

My agents and I built toolwitness.ai: it starts every new MCP server in a no-network sandbox and records what it does. A tool is listed only after scripted checks and independent AI reviews.

Read the toolwitness.ai case study
method

Multi-agent system.

My agents and I built an agent workflow harness. It gates sending, spending, deletion and release, and every change gets a review by a model from another lab. In one week (Nov 10 to 16, 2026) it dispatched 1,612 agent jobs; 1,308 ran to completion and 268 were recorded as failed.

models and agent tools
ProviderTool or model
AnthropicClaude Code
OpenAICodex
GoogleGemini
xAIGrok
stack

What I actually run.

Orchestration

Multi-agent systems
Claude Code
OpenAI Codex
Gemini
Grok

Languages

Programming languages

Python, PHP, TypeScript, JavaScript, SQL and Bash.

Python
PHP
TypeScript
JavaScript
SQL
Bash

Infrastructure

Self-hosted infrastructure

I run self-hosted Git, local model inference and backups with sampled restore tests.

Linux
Tailscale
Caddy
nginx
Docker
Cloudflare
MySQL
MariaDB

Model work

Evaluation and guardrails

LLM evaluation, guardrails, planted-bug tests and model routing.

Guardrails
LLM evaluation
Planted-bug tests
Model routing
production

Source-grounded pipelines.

My job pipeline rejects any answer that cannot quote its source word for word.

My agents and I built toolwitness.ai: it starts every new MCP server in a no-network sandbox and records what it does. A tool is listed only after scripted checks and independent AI reviews.

I run automated newsletter sites Monday, Wednesday and Friday. Each issue passes automated checks before it is sent. Read the case study.

cost control

Routing tasks by cost.

My router picks the lowest-cost capable model for eligible AI helper tasks.

standards

How I ship.

Checks are tested with planted bugs.

Every safety control I ship gets planted-bug tests and a second-model review.

Job-pipeline answers must quote the source.

My job pipeline rejects any answer that cannot quote its source word for word.

Code review

Every change gets a review by a model from another lab.

Copilot Business lab

In a GitHub Enterprise Cloud lab, for Copilot Business, I set new features to off by default, turned off web search, outside indexing and bring-your-own-key access, blocked public-code matches and turned on metrics.

who

Work history

Founder and Principal Engineer at IM-Empowered Inc. since 2010.
Power Organics, 2000-2023 (remote from 2010).
B.S. Computer Science, Business Administration minor, Southern Oregon University, 2010.

closing

Open to roles

Senior AI Platform Engineer. Remote preferred; Arizona hybrid case by case.

Resume (PDF)