REVEL is an AI robotics company developing physical intelligence for general-purpose humanoid robots. We capture the force, dexterity and intent of human work with our Neural Gambit wearable, and use it to train RAI, the intelligence that powers our robots. REVEL is headquartered in Palo Alto, California, with R&D and engineering facilities in Prague and Hradec Králové, Czech Republic. This role is on-site with our engineering team in the Czech Republic.
The intent layer is REVEL's core differentiator: reading neuromuscular signals 30-100 ms before motion. We're looking for a scientist to decode high-density surface EMG into force and intent.
Responsibilities
Build decoders that map HD-sEMG into continuous force and joint angles
Characterise and exploit the 30-100 ms intent window
Design capture and labelling protocols for the data-collection workstation
Collaborate with the robotics ML team to feed clean signal into RAI
Run rigorous experiments on signal quality, drift and cross-operator generalisation
Requirements
Experience with EMG, biosignals, or time-series machine learning
Strong signal-processing fundamentals
Proficiency in Python and PyTorch or JAX
Experimental rigour and the ability to work with noisy physiological data
Bonus qualifications
Background in neuroscience, biomechanics, or motor control
Experience with high-density electrode arrays
Familiarity with real-time inference constraints
Skills Required
- Experience with EMG, biosignals, or time-series machine learning
- Strong signal-processing fundamentals
- Proficiency in Python
- Proficiency in PyTorch or JAX
- Experimental rigour and ability to work with noisy physiological data
- Background in neuroscience, biomechanics, or motor control
- Experience with high-density electrode arrays
- Familiarity with real-time inference constraints
What We Do
REVEL is an AI robotics company developing physical intelligence for general-purpose humanoid robots. The company captures the force, dexterity, and intent of human work through its Neural Gambit wearable to train RAI, the intelligence powering its robots. It serves as a modern robotics technology firm providing training data, infrastructure tools, and an AI data layer for the next generation of humanoid robots.
