Senior Algorithm Engineer

Beacon Biosignals•Boston, MA

1d•Remote

About The Position

Beacon Biosignals is seeking a Senior Algorithm and Machine Learning Engineer to join its analytics and machine learning domain. The role works alongside data scientists, neuroscientists, engineers, and clinicians to scope, build, deploy, and maintain machine and deep learning models that analyze brain and biosignal data in support of sleep, neurological, and psychiatric therapy development. The engineer will participate in and lead the full biosignal-based algorithm development lifecycle for medical devices, from requirements and data curation through development, validation, production, maintenance, and documentation. The position also contributes to Beacon’s internal machine learning tools and engineering practices, presents results to stakeholders, and supports client-facing projects. This is a fully remote role based anywhere in the United States. Beacon also has in-person office hubs in Boston, New York City, and Paris.

Requirements

More than 5 years of industry experience in machine learning and deep learning, particularly in health sciences or other regulated fields.
A proven track record of bringing algorithms into production.
Experience with digital signal processing (DSP) and statistics, and the ability to select an appropriate tool for the problem.
Proficiency with PyTorch (preferred) or another deep learning framework for training, developing, and deploying deep learning models.
Proficiency with current deep learning advances, including Transformers/ViT, large-scale modeling, and large-model training.
Knowledge of software and ML engineering practices, including testing, version control, code reviews, documentation, Dockerization, CI/CD, and experiment tracking.
Experience with biosignals, medical imaging data, or large time-series datasets, or enthusiasm for learning about these domains.
Ability to collaborate in a team environment through open communication and continuous feedback.
Ability to explain and present complex technical topics appropriately to internal and external audiences.
Interest in participating in the entire algorithm development lifecycle, including formal validation, quality and regulatory documentation, production deployment, and client work.

Nice To Haves

PyTorch experience is preferred.
Experience with biosignals, medical imaging data, or large time-series datasets.

Responsibilities

Participate in and lead the full biosignal-based algorithm development lifecycle for medical devices, including specifications and requirements gathering, data curation and labeling, development, failure analysis, production, maintenance, and documentation.
Select, implement, and develop the most appropriate methods for each problem, including determining when deep learning or other approaches are most effective.
Enhance internal deep learning and machine learning tools to improve team efficiency, introduce model architectures and algorithmic techniques, and refine code for reusability and rapid experimentation.
Promote best practices so algorithm implementations are user-friendly, well-documented, and thoroughly tested, including unit tests, comprehensive documentation, CI, and non-regression testing.
Present results to key stakeholders and help them use algorithms in client engagement.
Support client-facing projects to understand and shape the impact of existing deployed algorithms and future algorithm development.
Work across scoping, data wrangling, experimentation, formal validation, quality and regulatory documentation, production deployment, and engagement with clients who may benefit from the algorithms.