Head of Machine Learning
Qureight Ltd
·Today
- Location
- Cambridge, England, United Kingdom · London, England, United Kingdom
- Workplace
- Hybrid
- Type
- Full-time
- Department
- Machine Learning
- Seniority
- Director
- Source
- Workable
Description
About us
Qureight’s mission is to accelerate clinical trials and ensure breakthroughs in lung and heart disease reach patients without delay. Our AI-powered data and imaging curation platform enables the analysis of clinical imaging and other healthcare data, helping our customers bring treatments to market, faster.
We’re looking for talented people who want their work to matter. With offices in Cambridge and London, you’ll join our multidisciplinary team of clinicians, scientists, and engineers. What unites us is our open culture, continuous learning mindset, and a shared mission to help biopharma run faster, smarter trials.
About the role
Qureight develops AI-powered quantitative imaging tools that help researchers and pharmaceutical partners understand lung disease and measure treatment effects. Our Machine Learning team is advancing two closely connected areas: foundation-model research on large-scale medical imaging data, and applied ML research and development of clinically useful models, including segmentation and quantification methods that generate quantitative CT biomarkers for active clinical-trial programmes.
We are looking for an experienced Head of Machine Learning to lead, develop and support this growing team. The role combines proven people leadership with a strong ML research and technical track record, including taking models into production: creating clarity of purpose, helping experienced scientists do their best work, nurturing emerging leaders, and building an environment where ambitious research and reliable delivery reinforce one another.
The successful candidate will bring substantive contributions to ML methods, models or their deployment alongside proven experience leading scientists and engineers. They will work with the CSO, Principal ML Scientists and the wider team to shape scientific direction, priorities and standards across foundation-model and applied ML programmes, partnering with Engineering and Platform to take research prototypes into dependable production use. They will remain engaged in research and technical review, provide scientific mentoring, communicate trade-offs openly and empower colleagues to take ownership rather than prescribe solutions unnecessarily.
What you will do
Provide credible scientific and technical leadership
- Guide and critically review technical approaches to self-supervised learning, representation learning, large-scale vision models, generative modelling, classification, segmentation and quantitative imaging models. Engage directly with experiments and code where this adds value, while respecting the team’s scientific ownership.
- Set and maintain standards for experimental design, meaningful benchmarks, cross-dataset model-performance validation, reproducibility and critical interpretation of results, supported by clear experiment records, code review and research documentation.
- Agree responsible use of AI-assisted coding and review tools, including LLMs, with Engineering, retaining human review and existing confidentiality, security and quality requirements.
- Encourage publication-quality innovation across foundation-model and applied ML programmes where existing methods fall short, while ensuring that work addresses clinically relevant questions. Contribute to the ML intellectual property portfolio with the CSO and relevant colleagues.
- Help researchers translate promising foundation-model capabilities and applied ML innovations into useful downstream applications, in close collaboration with applied ML and Data Science colleagues.
Lead, coach and develop a high-performing ML team
- Line manage senior ML staff, including Principal Scientists; provide regular developmental one-to-ones, constructive feedback, performance reviews and meaningful career pathways.
- Support Principal Scientists in their scientific and leadership development, including constructive technical challenge, mentoring and people-management capability; delegate ownership and decision-making at the appropriate level.
- Build a culture of trust, scientific rigour, openness and mutual respect in which people can challenge ideas, raise concerns early and contribute to decisions that affect their work.
- Plan hiring, succession, capacity and team development in partnership with the ML team and People & Organisation.
Set shared direction and manage a balanced scientific portfolio
- Work with the CSO and ML team to establish clear priorities, realistic milestones, roles and decision rights across foundation-model research and applied ML.
- Balance exploratory research across both programmes with model development, performance evaluation, software validation, production deployment and clinical-trial delivery commitments; make resource and priority trade-offs explicit.
- Revisit boundaries between foundation-model and applied activities as new models are specialised and deployed, encouraging shared expertise and avoiding unnecessary silos.
- Create transparent planning and communication practices that provide accountability while preserving appropriate autonomy in scientific methods.
Lead model delivery into products and clinical trials (partnering with Data Science and Engineering)
- Lead the ML team’s contribution from prototype through production deployment, working with ML Engineering, Platform and Product. Agree ownership of model testing, release, monitoring, maintenance and continuous improvement.
- Work as a peer partner with the Head of Data Science on shared priorities, cross-team planning and strategic decisions where imaging models feed trial and research analyses. Agree biomarker requirements, validation evidence, versioning and release of model outputs for analysis, with clinical colleagues as appropriate.
- Oversee model-performance evaluation and software validation as distinct, complementary activities. Agree traceability, documentation and change-control responsibilities with ML Engineering, Quality and Regulatory colleagues, including the evidence needed for release under the applicable quality system.
- Represent the ML programme clearly to senior leadership, scientists, clients and collaborators, including limitations, risks, client value and realistic effort and delivery expectations; contribute these assessments to proposals.
- Partner with Platform and colleagues responsible for data operations to establish dependable dataset management, versioning, provenance and quality-control practices that support reproducible research and model delivery.