About Antonio Osorio, PhD
I help startups and companies build AI systems that actually work — combining enterprise engineering experience with scientific rigor.
Why Work With Me
Enterprise Patterns Without Enterprise Bureaucracy
I’ve spent 20+ years building software at scale — recommendation systems at Netflix serving hundreds of millions of users, analytics infrastructure at Amplitude processing billions of events, computational drug discovery at Schrödinger. I know what production-grade looks like, but I also know how to move fast and ship.
Scientific Rigor Without Academic Slowness
My PhD in computational physics taught me to think clearly about complex systems, quantify uncertainty, and design experiments that actually answer questions. I bring that rigor to AI strategy — but focused on outcomes, not papers.
Hands-On Building, Not Just Slides
I write code. I review PRs. I debug production issues at 2am when needed. Strategy matters, but so does execution. You get someone who can think at the architecture level and also get things working.
Background
The Path to AI Consulting
I started my career simulating atomic-scale systems — molecular dynamics, quantum mechanics, statistical physics. That foundation in computational thinking proved invaluable when I moved to enterprise software.
At Netflix, I helped build recommendation and experimentation systems. I learned how A/B testing, chaos engineering, and distributed systems work at massive scale.
At Amplitude, I developed analytics infrastructure processing billions of events daily. I gained expertise in data pipelines, real-time processing, and making data useful.
At Schrödinger, I bridged computational science and software engineering for drug discovery. I saw how rigorous scientific methods could be applied to practical problems.
Now I help companies apply these lessons to AI — building systems that are not just technically impressive, but actually useful and reliable.
Areas of Focus
AI/ML Systems
- Large Language Models and prompt engineering
- Retrieval-Augmented Generation (RAG) architectures
- AI safety and guardrails (constitutional AI, content filtering)
- Evaluation and monitoring for AI systems
Enterprise Engineering
- Distributed systems and microservices
- Data engineering and pipeline architecture
- Cloud infrastructure (AWS, GCP)
- Testing and observability
Technical Leadership
- Engineering team building and mentorship
- Architecture and technical strategy
- Cross-functional collaboration
- Startup-to-scale transitions
Education
PhD, Materials Engineering Focus: Computational Physics, Molecular Dynamics, Statistical Mechanics
| Get in Touch | Read Blog |