🎯 Senior AI Engineer @ Pro Football Focus
🧩 Founding Engineer @ Aucctus
Builder of intelligent systems that reason, learn, and adapt.
I believe great AI systems aren’t about making models smarter — they’re about making systems more deterministic around them.
LLMs are probabilistic engines; the craft is in architecting rules, constraints, and context layers that make their behavior predictable, traceable, and aligned with intent.
When building agentic systems, I follow principles like:
- Murphy’s Law of LLMs: Anything an LLM can misinterpret, it eventually will — unless the system prevents it.
- Context before capability: Reasoning improves when context is structured, not when models are oversized.
- Determinism by design: Every agent should have an observable plan, bounded actions, and measurable outputs.
My goal is to design reliable, explainable, and self-correcting intelligence — where uncertainty is contained by architecture, not hidden behind it.
- LLM & NLP Systems: NL-to-SQL, GraphRAG, Assertions-based learning
- Backend & Infra: FastAPI, Django, Elixir, Redis, Celery, AWS, Docker
- Agent Frameworks: ReAct orchestration, DAG-based state management, OpenTelemetry
- Frontend Work: React, LightningJS, and WebGL-driven experiences for intelligent UIs and visual systems
