Senior Algorithm Engineer (Machine Learning)

About the role

Beacon Biosignals is looking for a Machine Learning engineer to join its analytics and machine learning domain. You will work alongside data scientists, neuroscientists, engineers and clinicians to scope, build, deploy and maintain machine and deep learning models that analyse brain and biosignal data for sleep, neurological and psychiatric therapy development. The role is primarily remote for people based near Paris, with office hubs in Boston, New York City and Paris.

Key responsibilities

• Lead the full biosignal-based algorithm development lifecycle for medical devices, from specifications and requirements gathering through data curation and labeling, development, failure analysis, production, maintenance and documentation.
• Select and implement the most appropriate method for each problem, choosing deep learning when it fits and other methods otherwise.
• Improve internal deep learning and machine learning tools, introduce new model architectures and algorithmic techniques, and refine the codebase to encourage reusability.
• Share best practices so implementations are user-friendly, well documented and thoroughly tested, including unit tests, CI and non-regression testing.
• Present results to key stakeholders and help them use the algorithms for client engagement.
• Support client-facing projects to understand and shape the impact of Beacon's algorithms for customers, including existing deployed algorithms and future developments.

Required profile

• More than 4 years of industry experience in machine learning and deep learning, especially in health sciences or other regulated fields, with a track record of bringing algorithms into production.
• Experience with digital signal processing (DSP) and statistics, and a preference for using the right tool for the job.
• Familiarity with biosignals, medical imaging data or large time-series datasets, or enthusiasm to learn them.
• Able to explain complex technical topics clearly to different audiences, internally and externally.

Required skills

• PyTorch (preferred) or another deep learning framework for training, developing and deploying models.
• Knowledge of recent deep learning advances such as Transformers, ViTs, large-scale modeling and large model training.
• Software and ML engineering best practices: testing, version control, code reviews, documentation, Dockerization, CI/CD and experiment tracking.