AI Engineer | Performance Engineering → AI Automation | Lee's Summit, MO (Remote)

🚀 Open to remote contract or full-time roles — Performance Engineering, AI Engineering, or hybrid positions combining both. Active US Public Trust clearance.

I build production-grade data pipelines with LLM augmentation — multi-source aggregation, scoring engines, and human-in-the-loop feedback systems that turn user decisions into training data. My background is 24+ years in enterprise IT, with 14 years specializing in LoadRunner/performance engineering, which gives me a reliability-first perspective that most AI engineers don't have.

Currently building toward agentic and self-improving systems — using my own job search as the substrate.

A multi-source Python pipeline that aggregates jobs from 10+ sources nightly, scores them with a weighted multi-track classification engine, generates tailored cover letters via the Claude API, and delivers a ranked HTML email digest.

The system features a human-in-the-loop feedback loop — decisions submitted via Google Forms feed a permanent decision ledger (job_decisions.json) that's the foundation for K-Means clustering and future agentic refactoring. Every script pulls from GitHub at start and pushes at end, making the pipeline fully sync-able from any device.

Python Claude API Google Sheets API SMTP Git Automation K-Means Ready

Same pipeline architecture applied to cybersecurity job hunting — targeting SOC Analyst, MDR Analyst, Vulnerability Management, and Incident Response roles across Remote US and KC Metro markets. Features color-coded track scoring, self-healing filter logic, and autonomous nightly Git commits.

Python Cybersecurity Multi-track Scoring Production Pipeline

• 🧠 K-Means clustering on accumulated decision data — let unsupervised learning surface filter patterns the humans missed
• 🤖 Agentic refactor — replace rule-based scoring with LLM-driven control flow that adapts to feedback in real time
• 🔄 Replication target — apply the same pipeline pattern to a third domain (RFP scraping, news aggregation) to demonstrate the architecture is generalizable

• 24+ years enterprise IT (federal + telecommunications)
• 14 years hands-on LoadRunner/VuGen/LRE specialist
• Recent: Sr. Performance/QA Test Engineer at USDA — led performance testing for AWS/Kubernetes migrations, integrated AppDynamics/Splunk/Prometheus for observability, increased throughput 40%, reduced defect resolution time 35%
• Earlier: 9 years as a LoadRunner specialist at Sprint/CenturyLink, scaling systems to 12,000+ TPS
• Currently: IBM Generative AI Engineering Professional Certificate (Coursera, 2025–2026), AI Engineer Bootcamp (Udemy, 2025), AWS Cloud Practitioner

• Email: harichardson68@gmail.com
• LinkedIn: linkedin.com/in/hans-richardson
• Location: Lee's Summit, MO (Remote)

Available immediately for remote work. Open to W2, 1099, or full-time. Strongest fit: Performance Engineering with LoadRunner, AI Performance/Reliability Engineering, or AI Systems Engineering roles where reliability and observability matter.