A brief description about me
Generative AI Scientist with Production Skills
AI Research Engineer | PhD in AI
Hi there! I’m Gusseppe Bravo, a Generative AI Scientist with a PhD in AI, specializing in AI systems that adapt to real-world change. I built first-of-its-kind AI agents for production model monitoring and improvement (CAMA at AAMAS, KC-Agent at IEEE COMPSAC).
Currently building healthcare cognitive architectures at Cotiviti (Cotiviti press), after 7+ years of continual learning research at Barcelona Supercomputing Center/Lenovo (Lenovo press) and diabetic retinopathy research at Emory Medical Center. My PhD research achieved 99% storage reduction while maintaining 96.9% accuracy in privacy-sensitive healthcare (Springer Nature).
Some facts: I prototype fast. I measure everything (costs, latency, performance). I follow the old-school unix principles: do one thing well.
Highlights
- Generative AI Scientist at Cotiviti - building healthcare cognitive architectures and a cost-efficient 3D RAG system ($10 for 1k docs end-to-end, $3M-$5M annual revenue opportunity)
- PhD in AI, Cum laude - UPC BarcelonaTech, human-on-the-loop continual learning for model adaptation
- 15+ publications in top-tier AI venues (AAMAS, ICPR, VISAPP) and 40+ GitHub repos for open-source ML/MLOps
- $250K+ research funding and $10M+ revenue impact from AI fraud detection systems
Key Projects
- CAMA (cognitive_architecture_checker) - LLM-based agents that autonomously monitor and improve ML models in production. Featured at AAMAS 2025; developed with Lenovo AI Lab.
- Scanflow (scanflow) - production-grade MLOps framework for ML workflow management, debugging, and reliability. Published in Expert Systems With Applications.
Stack
Linux, Python, PyTorch, Numba, LangGraph, AutoGen, Langchain, transformers, MLflow, Ray, ChromaDB, Kubernetes, Node.js, Spark, LLMs
More
Publications - Talks - Portfolio - Full CV
Let’s Connect!
If you’re interested in connecting with me, feel free to send me a message or connect with me on LinkedIn!
