The interesting part of AI engineering is everything underneath the model call.
I build with a fleet of coding agents, and when a layer under them breaks or falls short, I fix it upstream.
Now: on-device speech for Apple Silicon, shipping localvoxtral and contributing the Voxtral realtime inference path to mlx-audio-swift.
Selected work
- localvoxtralSwift
Native macOS menu-bar app for realtime, fully local dictation: words appear while you’re still speaking, with optional on-device LLM polishing. Runs Mistral’s Voxtral Mini 4B Realtime on Apple Silicon.
- mlx-audio-swiftSwift
Contributor to the Voxtral realtime streaming path: incremental mel/conv front end (O(N²) → O(N) per utterance), fp16 dtype fixes, Metal buffer-pool policy. Streaming went from ~1.9× slower than realtime to a flat 0.76 RTF.
- llama.cppC++
Merged upstream: preserve Anthropic thinking blocks through the server’s message conversion (#20120).
- fastcontextPython
Read-only repository-exploration agent that coding agents delegate to over bash: cited file:line answers, not context noise.
- voxmlxPython
Realtime Voxtral transcription in MLX; my fork adds an OpenAI-Realtime-compatible WebSocket server and Metal memory caps, with 4-bit conversions on Hugging Face.
- pi-intl-segmenter-fallbackTypeScript
Diagnosed a V8 segfault on small-ICU Node builds, filed it upstream with a proposed patch, and shipped a pure-JS Intl.Segmenter fallback to npm the same day.