You will build the models that define Sentinel’s core value, moving beyond standard EEG analysis. Working in a regulated medical context, you will deploy background-conditioned architectures on-device with extremely limited memory. This role requires proving or disproving central architectural claims while navigating the unique constraints of physiological time-series data and quantization.
ML Engineer at Phanes Neurotechnology
Join Phanes Neurotechnology to build Sentinel, a revolutionary dry-electrode EEG cognitive monitoring platform. As an ML Engineer, you’ll be the architect of models that run on-device with just hundreds of kilobytes of memory, proving or disproving the central claims of a background-conditioned architecture. We aren't looking for a PhD or a long list of publications; we want someone who can spot data leakage a mile away and isn't afraid to find the 'trap' in our datasets. If you thrive on deciding the architecture rather than inheriting one, this is your chance to define the future of neurotechnology.
Want to apply for this role?
Jack finds you jobs at companies like Phanes Neurotechnology. Talk to Jack to get considered for roles that fit what you're great at.
Location
Remote
Compensation
Not Disclosed
Company
Phanes Neurotechnology
Role overview
Medical Technology1-10 employees
Phanes Neurotechnology is a London-based medical device company building tools for the nervous system, organised around three things: sensing it, acting through it, and restoring what has been lost.
What you will do
- Train and evaluate models on physiological time series, utilizing background-conditioned architectures to reduce false alarms at matched sensitivity.
- Quantize models to integer precision to fit within a few hundred kilobytes of accelerator memory without sacrificing calibrated uncertainty.
- Design and execute rigorous, patient-independent evaluations that survive scrutiny from medical regulators and stakeholders who demand honest reporting of null results.
Who this is a fit for
- Strong background in training models for physiological time-series data, with a deep understanding of why signal processing differs fundamentally from computer vision.
- Demonstrated experience in edge deployment and quantization, specifically working within highly constrained accelerator memory environments.
- A rigorous scientific mindset that prioritizes avoiding data leakage and false excellence over hitting metrics, with a willingness to argue against internal conclusions.
Why this role is remarkable
- Lead the development of the “Sentinel” platform, a dry-electrode EEG device moving beyond simple analysis to true background-conditioned cognitive monitoring.
- Join a project with a compute budget larger than current model requirements and data already confirmed through established university partners.
- Directly influence the core product architecture at a pre-launch stage where your findings determine whether the device succeeds as a medical-grade tool.
How Jack & Jill work together
I get to know what you’re great at, then find roles you’d never find yourself.Ok, I'll go first. I'm Jack, an AI that gets to know you on a quick call, learning what you're great at and what you want from your career. Then I help you land your dream job by finding unmissable opportunities as they come up, supporting you with applications, interview prep, and moral support.
I recruit from Jack’s network and make the intro when I spot a great match.And I'm Jill, an AI Recruiter who talks to companies to understand who they're looking to hire. Then I recruit from Jack's network, making an introduction when I spot an excellent candidate.
Jack gets to know what you're great at and what you want next, then searches 15 million jobs daily and helps you discover roles at companies like this.
Meet Jack
What happens next?
Jack’s an AI agent for job searching and career coaching. He works for you.
Jill is the AI recruiter working for the company. She recruits from Jack’s network.
If your profile’s a match and Phanes Neurotechnology wants to meet, Jill will make the intro. In the meantime, Jack will send you excellent alternatives.