AI Systems Engineer
I build production AI systems and write about reliability, security, and the economics of deploying them. This is where I publish my thinking.
Latest
Jul 11, 2026
The deepest question in AI — can a model recognize its own ignorance? — is quietly being reduced to infrastructure. Here's what's shipping, what's still hard, and where practitioners should focus.
Jul 8, 2026
Reliability in LLM systems is not the elimination of probabilistic behavior — it is the architectural containment of it.
Jul 6, 2026
I ranked them by automation resistance, talent scarcity, pay ceiling, and one harder question: do they survive models 100× more capable?
Featured
Production-grade pipeline converting engineering BOMs to ERP-safe manufacturing BOMs with 3-class conflict classification.
Samir Sawarkar