Last updated:

Building

  • Working on inference optimization tooling — making LLMs faster and cheaper to serve at scale.
  • Prototyping a search system that understands technical documentation semantically.
  • Experimenting with event-driven architectures for real-time ML pipelines.

Learning

  • Category theory and its applications to software architecture.
  • Deep dive into Raft consensus and distributed state machines.
  • Exploring formal verification methods for critical systems.

Reading

  • Designing Data-Intensive Applications by Martin Kleppmann (re-reading)
  • The Art of Doing Science and Engineering by Richard Hamming
  • Various papers on retrieval-augmented generation and hybrid search

Thinking About

  • How to build developer tools that don't fight the user's mental model.
  • The gap between ML research and production engineering, and who should close it.
  • Whether to start writing a longer-form technical essay series.