I'm a software engineer. For the last several years I've worked on the machinery underneath large language models — the routers, schedulers, and storage layers that keep inference cheap and predictable at scale.
Before that I spent a long time writing client software, mostly on Flutter. The two halves of the job inform each other more than I expected: latency budgets, the cost of a wrong abstraction, the value of plain code.
I write here when I have something I'd want to read myself.
Essays · Selected
Under the await Line: How Swift Concurrency Really Works
What do the Swift compiler and runtime actually do when you write await? The state-machine transformation, the hidden async frame on the heap, which locals get saved, the difference between suspend and block, and why this design gives you clean stack traces — a deep but readable tour.
Stack and Heap: How a Program's Memory Actually Works
What stack and heap are, how a program carves up RAM, why one is 'free' and the other 'managed'. A language-agnostic walkthrough with Swift (struct/class, ARC) and Dart (reference type, Smi, GC) examples.
Living Memory — From Event Streams to Memories with NATS · Mnemo Series 4/5
The 'dead' feel of Mnemo's first weeks, the philosophy of piping each service's events into a separate memory layer, the math of a two-stage pipeline, and the stubbornness to solve dedup without adding Redis.
Secrets Have Nowhere to Go — The Birth of Vault · Vault Series 1/3
The day I had to send a signed APK to the test team and a .env to a friend, I realized: sensitive files don't have a real home. This is the story of how a discomfort turned into an infrastructure decision.
Work
I work on inference infrastructure — request routing, GPU scheduling, and the storage shapes that sit alongside them. Most of what I build is invisible to the people it serves, and I prefer it that way.
Earlier in my career I worked on client software, including a long stretch in Flutter; that work taught me to take latency, accessibility, and the small textures of an interface as seriously as anything on the server.
Open to thoughtful conversation, occasional advising, and rarely a new seat. Write to me — I read everything.