Senior Staff Engineer at Meta leading Voice AI infrastructure for Ray-Ban smart glasses. Founder of three startups. Building at the edge of audio, ML, and real-time systems.
I'm a systems engineer building at the intersection of real-time audio, on-device ML, and AI infrastructure. At Meta, I lead the Voice AI Platform -- an 8-stage streaming audio pipeline that powers always-on ambient intelligence on Ray-Ban Meta smart glasses, from dual-microphone capture at 48 kHz through privacy-preserving transcription in trusted execution environments to multi-modal retrieval over weeks of conversational memory.
Outside Meta, I build products. I'm the founder of three startups spanning AI-native documents, private social sharing, and enterprise data infrastructure. I care about shipping things that work, building systems that scale, and the craft of turning research into products people use every day.
AI-native document platform for agents and humans
A document platform built for the agent era. Any AI agent can publish a polished, hosted web document with a single API call -- no auth required, instant URL, full editing and collaboration from the moment it lands. As AI agents become primary content creators, they need a native output layer that goes beyond markdown dumps and terminal logs.
Agents get a clean POST-HTML-get-URL API, MCP server integration, and a forward proxy. Humans get real-time collaboration, AI-powered Docsmith chat, native PDF viewing with annotation, version history, and Google Docs export.
Nurture your friendships -- plan memories, events & trips
A private social app designed for the people who actually matter -- your close friends. A digital rolodex meets shared journal: collect and revisit memories, plan events and trips, and build a living archive of your friendships, away from the noise of public social media. No algorithms, no strangers, no performative posting.
Customized ETL for enterprise marketing data
Custom data pipelines for enterprise marketing teams that have outgrown off-the-shelf ETL tools. Bespoke pipelines tailored to each customer's stack and data model -- extraction from all major marketing platforms, schema normalization, cross-touchpoint identity resolution, and clean delivery into the customer's warehouse. A single source of truth for spend, performance, and attribution.