Staff Machine Learning Engineer, Sensors & Intelligence

Tonal

5d•Remote

About The Position

Tonal is seeking a Staff Machine Learning Engineer for its Sensors & Intelligence team to develop foundation models of human movement and physiology. The role sits at the intersection of machine learning, biomechanics, physiology, and computer vision, using multimodal workout data from cable force and position sensors, cameras, and wearable trackers. The resulting representations will support adaptive coaching, form feedback, personalized progression, and musculoskeletal health models. The position combines foundational research with product-facing development. The engineer will help define research directions, conduct rigorous experiments, publish research, and partner with engineering to bring methods into products. It is remote-first and based in Toronto, Ontario; candidates in Canada and the United States are welcome.

Requirements

Strong track record as an independent researcher, with publications in relevant venues such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, IMWUT/UbiComp, CHI, IEEE TBME, Journal of Biomechanics, or similar.
Deep expertise in at least one of sensor fusion, biomechanics, physiological signal modeling, or computer vision for human motion.
Hands-on experience designing, training, and debugging transformer architectures, including attention mechanisms, time-series positional encoding, and multimodal tokenization.
Ability to train and develop machine-learning models end to end in PyTorch, JAX, or TensorFlow, from data curation through experimentation and analysis.
Strong grounding in signal processing, including filtering, calibration, time alignment, and frequency-domain analysis.
Experience with rigorous experimental design, including building ablations, avoiding subject-level data leakage, and distinguishing meaningful gains from noise.
Ability to independently define and drive ambiguous research problems toward measurable product impact.
Clear communication skills for explaining complex findings to scientists, engineers, and product leaders.

Nice To Haves

Experience pretraining or scaling foundation models, including distributed training and understanding scaling behavior.
Familiarity with musculoskeletal modeling tools such as OpenSim, MuJoCo, or MyoSim, or with physics-informed machine learning.
Experience with wearable physiological signals such as IMU, PPG, HRV, or EMG data.
Experience with personalization, few-shot adaptation, or uncertainty quantification.
Experience with model compression or efficient architectures for edge deployment.
Background in human-subjects research, data collection protocols, or validation studies.
Interest in fitness, sports science, or digital health.
PhD in Computer Science, Electrical Engineering, Biomedical Engineering, Biomechanics, or a related field; equivalent depth demonstrated through research experience and publications is also welcomed.

Responsibilities

Lead research and development of multimodal foundation models that learn from synchronized sensor, video, and physiological signals.
Design self-supervised pretraining strategies for long, heterogeneous time-series data.
Develop sensor-fusion approaches addressing different sampling rates, sensor noise, synchronization error, and missing modalities.
Advance computer-vision methods for 2D and 3D human pose estimation, motion reconstruction, and movement quality assessment.
Build models to estimate biomechanical and physiological quantities, including joint kinematics, load, effort, fatigue, and recovery.
Define evaluation frameworks and benchmarks to measure generalization across users, body types, movements, and equipment conditions.
Validate model outputs against gold-standard references such as motion capture, force plates, and clinical-grade physiological sensors.
Partner with ML Engineering to adapt research models for cloud deployment and on-device inference.
Publish regularly at leading venues and represent Tonal in the research community through papers, talks, and collaborations.
Mentor scientists and engineers and help set the scientific direction of the Sensors & Intelligence team.