Principal Data Scientist

About the role

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.