Building AI that automates the SDLC — Bogotá, Colombia 🇨🇴 · open to remote
I build the agentic-AI systems that automate the software delivery lifecycle — not just test code, but the processes and workflows around it.
As Advanced Quality Assurance Engineer at Simetrik, I lead AI-driven automation: orchestrating LLM agents, RAG pipelines, MCP servers, and custom skills/plugins (built with Claude Code and Antigravity) that plan, generate, execute and self-correct.
My edge is engineering rigor: I'm a Software Engineer grounded in quality, reliability and security — years of Python/Pytest automation, CI/CD, AWS, and security testing (OWASP ZAP). That production discipline is what most AI projects lack.
Heading toward → AI DevSecOps: autonomous agentic systems across the SDLC, with a security lens.
- 🧰 MCP server for QA/SDLC — exposing agent-callable tools for test generation & execution
- 🧪 AI Evals Harness — "QA for AI": LLM-as-judge, prompt regression, accuracy/recall metrics
- 🎵 hgmlyrics — adding semantic search (RAG: pgvector + embeddings)
- 🔌 An open-source Claude Code skill/plugin
🥈 2nd Place — Habi AI Hackathon w/ Microsoft & Azure (Jan 2025)
🏅 Hall of Fame — Habi's "We are curious and learn by doing" (Dec 2024)
☁️ AWS Cloud Practitioner — Certified (2024)
🎓 Software Engineering — Politécnico Grancolombiano (Final year, 2026)
🎓 Academic projects → @S4muelDP


