// about

Where silicon learns to think

RISC-V compilers, ML compiler-driven runtime generation, and RTOS integration for edge AI mixed-signal accelerators. I work at the layer where neural networks meet custom silicon — compiled to run fast, run local, and run on hardware that doesn’t need the cloud.

Home Writing Notes About Subscribe

What I work on

Edge AI mixed-signal accelerators — RISC-V compilers, ML compiler-driven runtime generation, and RTOS integration for custom silicon
Compute-in-memory — the software stack that compiles neural networks onto analog crossbar arrays, running inference at the edge without the cloud
Open source — OpenClaw plugins and extensions, personal AI agents

How I build

Claude-pilled. Claw-pilled. Everything lands on GitHub. I believe in building in public, shipping fast, and sharing what I learn along the way.

Also tinkering with

Self-hosting & homelab — Proxmox, MikroTik, Cloudflare tunnels, Tailscale
Network security — firewall hardening, router configuration, defense-in-depth for home and lab networks

Connect