Location
Cambridge, UK | Nashville, USA
Department
Research, Algorithms & Engineering
Employment Type
Full-time | Hybrid
About The Role
As an On-Device ML Engineer, you will develop machine-learning models that run directly on ear-worn devices. Your work will focus on extracting reliable cardiovascular and autonomic health signals from noisy, real-world data under strict compute and power constraints.
What you’ll do
- Develop signal-processing and physiological-inference algorithms for multimodal in-ear bio-signals (PPG, acoustics, IMU, temperature).
- Build methods that convert noisy, real-world data into reliable cardiovascular and autonomic health metrics.
- Lead algorithm pipelines from signal cleaning to model design, validation, and prototype integration.
- Work closely with hardware and firmware teams to optimise end-to-end sensing systems.
- Advance hybrid DSP + ML approaches for ear-based health sensing.
- Contribute to OmniBuds’ roadmap for continuous BP estimation and hypertension-focused digital biomarkers.
What we expect
- Strong background in signal processing and applied machine learning.
- Experience deploying ML models on embedded or edge devices.
- Proficiency in Python; experience with C/C++ is a plus.
- Understanding of physiological signals and noisy sensor data.
- Ability to balance accuracy, efficiency, and robustness.
Why OmniBuds
You’ll work on problems few teams in the world are tackling—bringing continuous, medical-grade inference onto tiny devices worn all day, every day.
#J-18808-Ljbffr