About
I’m a software engineer with 12 years of consulting experience, mostly on large-scale infrastructure and cloud architecture, and recently focusing on LLMs, AI tooling and autonomous agent systems.
I enjoy working on systems that need to handle real scale: reliable backends, distributed setups that hold up under pressure, and agent designs that hold up in production without unnecessary complexity or cost surprises.
I consult because I like tackling the challenging problems that don’t come with easy answers. I write here to capture what I’ve learned along the way: the trade-offs, the tough spots, and the small shifts that help me get unstuck. A lot of these posts come from my own moments of second-guessing or frustration with unclear paths.
If you’re dealing with similar challenges around scale, reliability, or bringing AI agents into production, feel free to reach out.