Duties

Design and implement algorithms to extract physiological information from noisy biosensor data and optimize on-device computation
Partner with Firmware and Data Science teams to deploy artificial intelligence and machine learning models on edge devices
Optimize models for real-time inference on edge devices, including analysis and improvement of battery consumption patterns
Collaborate with the Signal Processing team to develop algorithms that personalize calculations based on member data
Research and design innovative algorithms to improve performance under edge-computation constraints
Contribute to software development, debugging, and validation to ensure production-ready code and reliable results
Build, train, and test machine learning models for large-scale data processing on edge devices
Collaborate with Product Managers to translate member needs into machine learning–based solutions

Requirements

Master's degree in Computer Science, Applied Mathematics, Electrical Engineering, Biomedical Engineering, or related field (or foreign degree equivalent)
At least 4 years of experience with signal processing and/or machine learning
At least 4 years of experience developing and implementing AI solutions for real-time processing on edge devices
At least 4 years of experience collaborating with cross-functional teams to understand requirements and design efficient edge computing solutions
At least 4 years of experience with biosensor systems and analyzing biomedical data
At least 4 years of experience with signal and image processing applications (C, C++, Python or MATLAB)
At least 4 years of experience with ML libraries such as scikit-learn, Tensorflow, PyTorch or Keras
At least 4 years of experience with statistical method and design of clinical studies
At least 4 years of experience with code and battery optimization on the edge
At least 4 years of experience adapting to changing requirements while producing high quality reports under tight deadlines