Principal Data Scientist
Confirmed on the employer's own hiring board on Oct 1, 2026. First seen by Alion on Oct 1, 2026.
At CoMind, we are developing a non-invasive neuromonitoring technology that will result in a new era of clinical brain monitoring. In joining us, you will be helping to create cutting-edge technologies that will improve how we diagnose and treat brain disorders, ultimately improving and saving the lives of patients across the world.
The Role
The Data Science team at CoMind develops the algorithms and machine learning systems that transform raw optical interference signals from CoMind One into continuous, clinically meaningful measurements of cerebral blood flow, intracranial pressure, and autoregulation. Working at the frontier of photonics, physiology, and applied ML, the team's work directly determines what CoMind One can measure, how accurately, and under what clinical conditions.
As Principal Data Scientist, you will be a technical authority for CoMind's data science function, setting methodological direction for signal condition and extraction, personally driving the most complex and highest-impact problems, and providing expert guidance on data science best practice across the team. This is a senior individual contributor role: you will not manage people directly, but your technical leadership will shape how the entire team approaches its most challenging problems. You will work closely with R&D, Clinical, and Software Engineering.
At CoMind, all team members work at least 4 days per week from our new Kings Cross offices, plus a flexible work-from-home day.
Responsibilities:
Act as the technical authority for the end-to-end signal processing and inference chain for CoMind’s technologies: from raw optical data through to clinical measurements
Set the methodological direction for estimation, signal extraction and ML modelling across the team: which approaches suit which problems, how they are evaluated, and what evidence is required before a method is trusted.
Own signal processing and analysis programmes from research through to validated, production-quality implementations with Software Engineering.
Derive achievable performance bounds from instrument and noise models, and use them to drive algorithm selection, requirement setting and design trade-offs
Own how the team handles uncertainty and calibration - inference methods appropriate to small clinical cohorts, per-patient estimation with quantified uncertainty, and calibration strategies that make measurements comparable across devices, sessions and patients.
Set the standard for how the data science function works: reproducibility, analysis and code review, experiment design, dataset governance and ground-truth definitions
Act as the primary technical reviewer and expert resource across the research organisation, reviewing technical reports, analysis plans and evaluation methodology, and holding the bar for methodological rigour and scientific integrity.
Identify and introduce new, best-practice methods from estimation, inference and measurement science in adjacent fields.
Act as a mentor to members of the Data Science teams and across the wider business
Contribute to CoMind's IP and publication strategy, authoring and reviewing technical papers, patent applications and regulatory documents.
AI is fundamental to our culture. It's not just a tool, but a core part of how we work, collaborate, and innovate. We expect all team members to embrace AI in their daily work and continuously find new ways to use it effectively.
Skills & Experience:
15+ years of experience in data science, ML, or applied research, with a strong track record of independent technical leadership on complex, ambiguous problems
A career working to extract small signals from noisy, complex physiological systems, and developing and deploying physical models of those systems to support those efforts.
Deep expertise in physiological time-series signal processing methodologies.
A demonstrated ability to take algorithmic work from research concept through to production-quality, validated implementations in shipped product.
Designing device performance evaluation methods where no prior gold-standard exists: simulating physical systems, running sensitivity analysis, identifying failure modes, and developing signal processing solutions to address those challenges.
Extensive experience owning calibration and cross-instrument comparability work that involved noise models, error budgets, and evaluation of experimental data
Strong record of scientific output: publications, patents, or equivalent evidence of original technical contribution and domain authority
Nice to Have:
Background in neuroscience, neuromonitoring, or cerebrovascular physiology
Experience with optical signal processing - e.g. LiDAR, pulse oximetry, NIRS, laser doppler flowmetry, or related technologies
Experience in a regulated industry (medical devices, diagnostics, pharma, or similar), with familiarity of algorithm validation and documentation requirements for software as a medical device
Benefits:
Company equity plan so all employees share in the success of the company
Salary-sacrifice pension scheme
Private medical, dental and vision insurance (medical history disregarded)
Group life assurance at 4x annual income
Comprehensive mental health support, including unlimited access to 1:1 sessions with trained professionals
Unlimited holiday allowance (+ bank holidays) and one week of remote working per quarter
Lunch voucher (£10) every day for JustEat and free dinner on those days where you need to work later
Twice weekly deliveries of fresh fruit and an extensive selection of snacks and drinks
YuLife subscription, allowing you to turn your daily steps and meditation into discounts at a range of stores
Access to Udemy for upskilling and professional development
Disclaimer - We use Granola, an AI notetaker, throughout our interview process to help capture notes. It's used only for note-taking during the conversation. Transcripts aren't saved to shared drives or stored externally. Let us know if you'd prefer we don't.