I build robust AI & LLM retrieval systems — from research prototypes to production-ready pipelines.
- Software Engineer & Applied AI, focused on language models, vector search & information retrieval.
- Passionate about making reliable, reproducible ML pipelines: containerization, monitoring, logging, guardrails & fallbacks.
- Always exploring the frontier between theory and practice: from differential geometry & topology to explainable AI, RL, and game theory.
(Also up for a chess or poker game!)
- Legal/Healthcare Search & Re-Ranking Hybrid & Dense Embeddings. Elasticsearch, Solr, Vespa. RRE & Quepid
- Retrieval-Augmented Generation (RAG): built rag-prototype — agents & LLM apps.
- Infrastructure: deliver production-ready APIs & services with Docker, FastAPI, CI/CD, and reproducible pipelines.
- OpenSource: OS Search, OSINT. Tools, Prompting & Docs: LM-Stacks, RepoGPT
- LLM-consensous, query expansion, and synthetic-data generation
- Game-Theory RL: apply MCTS, CFR/DeepCFR, and Regret Matching to games research.
- 🌐 Website: python-lair.space
- 👨🏻💻 GitHub: MrCabss69
- ✍️ Medium: @IntrinsicalAI
- 📰 Instagram: Intrinsical-AI
- 🐦 X / Twitter: @IntrinsicalAI
“Gravity explains the motions of the planets, but it cannot explain who set the planets in motion.”