**About the role**
You will bring a deep understanding of human movement and physical interaction into the same research loop as our robot-learning engineers. You will design experiments and computational representations spanning muscle activity, force, pressure, tactile contact, motion, and touch feedback. The goal is to determine which structure can be measured reliably and transferred across people, tasks, sensors, and robot embodiments. This is an engineering role: ideas should become code, datasets, models, and robot experiments.
**What you’ll do**
* Develop signal-processing and learning methods for synchronized EMG, force, tactile, pressure, motion, and visual data.
* Design experiments and sensor configurations that capture how humans regulate contact, stability, coordination, and effort during manipulation.
* Build multimodal representations that connect neuromuscular activity with external forces and touch feedback.
* Develop calibration and domain-adaptation methods that remain reliable across people, sessions, tasks, and sensor configurations.
* Create data-collection protocols grounded in biomechanics and downstream robot-learning needs.
* Work with robot-learning researchers to test whether physical-interaction representations improve policy behavior and cross-embodiment transfer.
* Influence wearable sensing, force and tactile hardware, validation procedures, and future measurement systems.
**What we’re looking for**
* Research or engineering depth in biomechanics, neuroengineering, biomedical engineering, motor control, computational neuroscience, haptics, kinesiology, or a related field.
* Hands-on experience collecting and analyzing one or more forms of biomechanical or physiological data, such as EMG, force, pressure, tactile sensing, motion capture, or wearable-sensor data.
* Strong quantitative skills in signal processing, statistics, time-series modeling, sensor fusion, or machine learning.
* Fluency in Python and the ability to build reliable modeling pipelines around imperfect, synchronized sensor data.
* Interest in connecting human physical interaction with learned robot behavior; a PhD is welcome but not required when equivalent depth is demonstrated through other work.
**Working at Relari**
Relari is a small research and engineering startup developing new ways for robots to learn dexterous skills from human biomechanics. Our founders have AI research roots at MIT and NVIDIA, along with autonomous-vehicle and robotics deployment experience at Pony AI and Dexterity. We are backed by top investors including Y Combinator, General Catalyst, and Soma Capital. You will work directly with the founders, own problems end to end, and test your ideas on real robotic systems. This role is full-time and on-site in San Francisco.
Visa sponsorship is offered for this role.
