Beacon Biosignals | Senior Machine Learning Engineer |Boston, MA | Onsite Available, Remote Friendly | Full Time
About Us:
Despite its significant potential for improving patient outcomes, brain monitoring is still not easily accessible or interpretable in clinical settings. We're going to fix that, and we'd like you to help.
We're founded by numerical programmers, neuroscientists, ML researchers, and practicing neurologists who are committed to translating our best-of-breed clinical research from the lab into hospitals and beyond. We're well-funded, well-connected, and own a well-labeled set of brain data amassed over the past decade at some of the most prestigious medical institutions in the world.
Our team is composed of neuro-experts, open-source enthusiasts, audio/DSP engineers, programming language nerds, and generally easy-going (but dedicated!) folks. We're adamant that...
- ...product development goes off the rails without rapid, early feedback from real users.
- ...honest, frequent, and open communication are more significant contributors to software development than technical wizardry.
- ...diversity is an integral part of strong engineering culture. Differing viewpoints are borne from differing backgrounds, and lack of diversity contributes to stagnation.
About You:
- You realize that lowering hypothesis test turnaround time from months to minutes requires applying best-of-breed DevOps concepts to the data science workflow.
- You can't wait to combine your background with our unprecedented EEG dataset to blow published statistical EEG results out of the water.
- You will discover and formulate techniques for analysis that haven't even been attempted with EEG outside of Beacon due to lack of data and/or infrastructure (e.g. "How might we refactor our existing spike detection algorithm to achieve high inter-rater agreement on noisy signals across a reduced set of channels?")
- You'll help develop new methodologies for aggregating a vast quantity of labels from expert neurologist readers of differing backgrounds and opinions.
- You've developed a solid, heavily-exercised workflow for debugging model performance; you now know more about the limitations of automatic differentiation and distributed heterogeneous computing than you ever thought you would when you started your ML journey (e.g. "How can I alter this model's architecture to mitigate the decrease in sample throughput once I lower the minibatch size?")
- You will help steer engineering efforts to standardize, improve, and automate our model development/deployment lifecycle and related tooling.
- You'll provide constant feedback about what we do wrong and how we can do better.
- As Beacon grows, you'll have the opportunity to build and lead teams that accomplish all of the above - tenfold!
- You'll have the opportunity to co-author scientific papers whose impact pushes the neurocritical care, neuroscience, and machine learning communities past contemporary limitations.
- PhD in relevant field or equivalent research engineering experience.
Our data science team makes heavy use of the Julia language. This quarter, we're pushing >70TB of signal data (and our processes for manipulating it) into AWS, where we're developing a deep learning platform for rapid hypothesis testing, sleek data visualization, and interactive analysis exploration. Come help us make the right decisions!
Contact Email is hidden if interested.