From promising model
to dependable system.
My work connects production AI, machine-learning architecture, and the platforms beneath them. The common question is simple: what has to be true before this system can be trusted?
I'm an ML and platform engineer. I work at the point where a promising model has to become a dependable system: productionising machine learning that reads the earth's subsurface while building the data platform, landing zones, and architecture beneath it.
Before that I built real-time odds-prediction systems and worked on cloud architecture at scale. Outside my day job I ship and operate SortedOut↗, and build experimental AI systems in the open.
Code with Numbers is where I turn that experience into practical guidance: the implementation details, architecture decisions, verification methods, and operational trade-offs that determine whether an AI or ML system holds up in production.
Production ML
Moving 3D subsurface models from notebooks into production workflows.
Systems at scale
Real-time prediction systems, cloud architecture, and data-platform foundations.
Products end to end
Shipping and operating independent products and experimental AI systems.
Working on a system
that has to hold up?
If you are wrestling with agents, ML infrastructure, or the operational trade-offs between them, tell me what you are building.
Email is the best way to reach me. I read every message and reply myself.
Email Asifcodewithnumbers@gmail.com