About this role
**About Preload**
Preload builds the data layer for physical AI. Robots learn mostly from video, but human interaction is much richer: touch, force, and muscle activity. We build a wearable multimodal stack (egocentric video, tactile gloves, EMG) to capture how people actually interact with the physical world, and turn it into datasets robotics teams can train on. We're a YC (F26) team of PhD founders from Johns Hopkins and Caltech with backgrounds at Neuralink, Paradromics, and other neurotech companies.
**The role**
You'll turn raw, noisy biosignals into features and models that make our data useful for physical AI.
**What you'll do**
- Build feature extraction pipelines for EMG, tactile, and kinematic signals
- Time-align and fuse multimodal streams (video, touch, muscle activity)
- Develop models and representations of human manipulation and motor intent
- Define data quality metrics and help shape what we collect next
- Work closely with sensor and robotics teammates to close the loop from hardware to model
**What we're looking for**
- 2+ years working with time-series or biosignal data (EMG, EEG, IMU, neural recordings, or similar)
- Strong Python and ML fundamentals (PyTorch or similar)
- Solid signal processing skills: filtering, artifact removal, synchronization
- Experience with multimodal or self-supervised learning is a plus
- Background in neuroengineering, BME, robotics, or related fields is a plus
**Why join**
Early, in-person team in San Francisco. You'll own core technical decisions from day one.