What are the responsibilities and job description for the Machine Learning Applied Scientist - Neuroscience position at Precision Neuroscience?
Department: Precision
Location: Santa Clara, California
Precision Neuroscience is pioneering a brain implant, known as a brain-computer interface (BCI), to restore communication and independence for people with neurological conditions. Our cutting-edge technology is designed to empower people with paralysis to control digital devices—such as computers and smartphones—with their thoughts alone, opening new possibilities for daily life.
Precision's multidisciplinary team brings together leading experts in diverse fields such as neurosurgery, artificial intelligence, machine learning, microfabrication, electrical engineering, and more. We are committed to turning breakthrough scientific advancements into real-world solutions for people affected by conditions such as spinal cord injury, stroke, and ALS.
As a Precision employee, you will be joining one of the fastest moving and best-capitalized companies in the emerging field of BCI. Since our founding in 2021, Precision has secured over $155 million in funding, developed and validated our technology, and initiated human trials in collaboration with some of the nation's top hospitals.
We are seeking aMachine Learning Applied Scientist - Neuroscience to join our mission of advancing brain-computer interface technology by implementing highly reliable motor/speech neural decoding algorithms. As an ML Applied Scientist, you will play a crucial role in developing the algorithms that enable our revolutionary BCI platform to transform patients' lives. You'll work on complex technical challenges at the intersection of neuroscience and computing, from real-time neural signal processing to intuitive user interfaces that help patients regain their independence.
This position is on-site at least 3 days a week at our Santa Clara or New York offices. We are unable to consider remote workers or people not currently based in the United States, and who do not have working rights. Travel up to 20% to clinical sites and to collaborate with team mates in other sites.
Key Responsibilities
Literature Review - stay at the cutting edge of neural decoding and relevant neuroscience research. Conduct periodic updates to the team on the evolving state of the art.
Experiment Design - design experimental protocols to gather training data. Collaborate with software engineers to implement these protocols. Collaborate closely with the clinical team to execute these protocols.
Neural Decoding - build proof of concept demonstrations indicating the feasibility of decoding various user intentions. This includes determining the ideal array placement, developing signal cleaning algorithms and training deep learning models to decode signals.
ML Pipeline design - build cloud and local ML pipelines to clean data, perform model training and to validate model quality. Work with software engineers to integrate these with the overall ML ops pipeline.
Product Development - collaborate with other ML engineers to integrate the proof of concept neural decoding ML models into production deep learning models. Work with software engineers, product managers and UX to integrate the algorithms into the overall product while meeting product and code quality requirements as well as delivery dates.
Execution - participate in project planning, team meetings, sprint meetings, code reviews, architecture meetings, create status updates. Also create and maintain documentation required by regulatory bodies like the FDA.
- BS in computer science or equivalent, PhD in neural decoding of either speech or motor signals, with extensive coursework and/or research in deep learning. Ideally 2 years industry/post doc experience.
- Experience with designing and conducting clinical experiments, ideally involving human subjects.
- Strong python programming skills using frameworks like python, numpy and pytorch to train deep learning models.
- Strong experience leveraging cloud platforms for training deep learning models at scale. AWS experience is strongly preferred.
- Strong deep learning fundamentals and a broad knowledge of deep learning algorithms. Knowledge of state of the art ASR/NLP algorithms is a strong plus.
- Experience with digital signal processing and neural signal preprocessing.
- Publication record at reputable neuroscience and/or ML conferences
- Strong plus: knowledge of C , realtime systems, embedded systems
- Strong plus: Medical device experience
- Strong plus: working with hardware
As an equal opportunity employer, Precision does not discriminate on the basis of sex, race, religion, national origin, disability status, protected veteran status, or any other characteristic protected by law.
