At WHOOP, we're on a mission to unlock and inspire performance for life. WHOOP empowers members to perform at a higher level through a deeper understanding of their bodies and daily lives. Our wearable technology collects rich physiological data, providing members with actionable insights into their recovery, training, and sleep.
We are seeking a Senior Signal Processing Engineer to develop and deploy algorithms for physiological sensors including optical sensor and inertial measurement unit (IMU) data into accurate, reliable, and real-time insights on WHOOP devices. This hands-on role centers on digital and statistical signal processing, sensor fusion, and model-based state estimation, with a particular focus on accelerometer and gyroscope data.
You will own algorithm development from sensor characterization, mathematical modeling, and Python prototyping through efficient C/C++ implementation, firmware integration, and production validation. Working closely with Firmware, Hardware, Data Science, and Product, you will deliver robust on-device algorithms that perform reliably across diverse members and real-world conditions while meeting the constraints of wearable hardware.
RESPONSIBILITIES
- Design and develop real-time signal processing and sensor fusion algorithms that combine Sensor measurements inputs to characterize motion and deliver reliable member-facing insights.
- Develop and tune model-based estimators for orientation and motion, including sensor bias estimation, uncertainty propagation, and drift mitigation under changing movement and sensing conditions.
- Build robust IMU processing pipelines, including filtering, calibration, time synchronization, resampling, coordinate transformations, and compensation for sensor noise and systematic errors.
- Analyze large-scale, noisy wearable datasets to identify failure modes and improve robustness across motion patterns, device orientation, fit, and individual movement characteristics.
- Translate algorithm prototypes into production-ready C/C++ implementations, balancing accuracy with power, memory, compute, numerical stability, and latency.
- Partner with Firmware and Hardware teams on sensor configuration, sampling strategies, and on-device integration; investigate differences between prototype behavior and performance on target hardware.
- Define performance metrics and rigorous validation plans using reference measurements, controlled experiments, real-world data, and on-device testing to assess accuracy, robustness, and long-duration stability.
- Own technical decisions for complex algorithm components, contribute to design and code reviews, mentor teammates, and collaborate across functions to investigate post-deployment issues and drive continuous improvement.
QUALIFICATIONS
- 5+ years of experience developing and deploying signal processing, sensor fusion, or state-estimation algorithms for real-world sensor applications, including substantial hands-on work with IMU data.
- MS or PhD in Electrical Engineering, Biomedical Engineering, Computer Science, Applied Mathematics, or a related quantitative field, or equivalent practical experience.
- Strong foundation in digital and statistical signal processing, including filtering, spectral analysis, stochastic processes, and sensor noise characterization.
- Demonstrated experience with accelerometer and gyroscope processing, IMU calibration, sensor error modeling, bias estimation, and drift management.
- Strong experience with Kalman filtering, including extended or error-state formulations, and model-based sensor fusion; practical understanding of nonlinear estimation, uncertainty propagation, and estimator failure modes.
- Practical knowledge of 3D motion and orientation representations, including coordinate frames, rotation matrices, quaternions, and rigid-body kinematics.
- Proficiency in Python for algorithm development, data analysis, and experimentation, and C/C++ for efficient embedded implementation;…