Senior Applied CV / ML Scientist — New York
Machine learning for things that actually ship
I own the path from research question to shipped product: data, models, deployment. Ten-plus years on phones, in cars, and on low-power servers — lately, generating the training data that doesn’t exist yet.
70%Shorter research-to-production cycle
40%Share of customer redaction usage
32%Recall gain at 90% precision
2Issued patents, 2 more pending
8 projects2013 — 20213 categories
Selected work
All work →CLIP Exercise Recognition
Zero-shot exercise classification from CLIP embeddings — no labelled training set required.
Side project2021
DAGER: Deep Age, Gender and Emotion Recognition
Deep facial analytics shipped across a commercial product line, running on-device.
Product2020
Driver Awareness
In-cabin attention monitoring — gaze and head pose under real automotive lighting.
Product2020
License Plate Recognition
Deep LPR system improving on the legacy pipeline by 20% in production.
Product2018
Car Make, Model and Color Recognition
Fine-grained vehicle attribute recognition from a single frame, in traffic.
Product2018
Video Face Recognition
CVPR 2013 — mean sequence sparse representation classification on movie trailers.
Research2013
1 postSince 2021