Currently: Founding Engineer at a stealth startup.
I spent three years at Google working on job scheduling and resource management infrastructure for an internal workflow engine. Before that, I did my master's in CS at Columbia, after two years at Samsung R&D mostly building apps for smart fridges (lol), and before that, my bachelor's in CS at IIT Bombay.
These days I mess around with local models a lot.
Recent work:
- mlx-qwen3-tts-longform: long-form narration in one cloned voice with Qwen3-TTS on MLX, at about realtime on a base M3
- longecho: the original; I'd initially done this for Echo-TTS. It runs on PyTorch with an NVIDIA GPU.
My profile picture is from when I used to need glasses. I've since had LASIK done, lol.
