whoami
Notes on distributed systems, applied AI, and the things I build after hours.
I'm a software architect working on enterprise GenAI platforms. This is where I write up what I learn — mostly Java/Spring, AWS, multi-agent systems, and the occasional side project.
Writing
- How an LLM thinks: from a bedtime story to Q, K and V Start with the version you could tell a five-year-old, then zoom all the way in: tokens, embeddings, attention, how W_Q, W_K and W_V are learned, and what actually happens when a model answers you.
- Lessons from running a multi-agent assistant in production What broke, what we monitored for, and why a simpler agent graph beat a clever one.
- Event streams over cron: rethinking a lead-scoring pipeline Swapping a nightly batch job for Kafka and Lambda cut lead response time from hours to seconds.
- Spring Boot patterns that actually scale The handful of decisions — connection pooling, idempotency, circuit breakers — that matter more than the framework choice.
Projects
-
MarkOut
Turns messy AI chat output into a clean, formatted document in one paste.
in progress → -
Signal Dashboard
A personal daily trade-signal dashboard for US equities and options.
in progress → -
Architecture Live
A live diagram that redraws itself from a running system's request traces.
early concept →