Data Scientist

Abtrace is solving one of the most complex and impactful challenges in healthcare: enabling primary care to deliver proactive, preventative care at scale.

Our team of doctors, researchers, software engineers and data scientists combines clinical expertise, advanced software engineering and AI to build clinical algorithms that help primary care clinicians identify risks earlier and intervene sooner.

We are building digital health technology that delivers personalised Population Health interventions at scale. Our platform continuously analyses patients’ health records to identify early signals of deterioration, emerging disease and opportunities for preventative care—helping clinicians act before problems become more serious.

Today, our technology is deployed across more than 600 primary care practices, supporting care for 7.5 million patients.

About the role:

We’re looking for a Data Scientist (Mid/Senior) to join our team. The core duty of the position will be the analysis of longitudinal healthcare datasets and development of predictive models from those datasets. The ideal candidate should have strong Python and SQL skills and be proficient in data science libraries such as scikit-learn, pandas and XGBoost, as well as transformer-based NLP techniques.

We are looking for someone who works well in a fast-moving team and communicates effectively with non-technical team members.

Responsibilities:

• Analyse large longitudinal clinical datasets.
• Work with complex, real-world structured data, addressing missing values and class imbalance and preventing label leakage.
• Design predictive algorithms and conduct machine learning experiments using clinical datasets.
• Validate and deploy models, monitor their performance and retrain them as needed.
• Collaborate with a small, close-knit and diverse multidisciplinary team of developers, data scientists and doctors.

Required skills:

• Proficiency in Python and SQL
• Excellent knowledge of machine learning and MLOps
• Experience with natural language processing (NLP), particularly transformer-based approaches
• Experience with AWS cloud infrastructure, including services such as SageMaker and Athena

Nice to have:

• Hands-on experience with dbt or a comparable data transformation framework
• Experience with time-series analysis, survival analysis, or longitudinal modelling

Company Benefits

• Private Pension
• Share Options scheme
• Generous sick and maternity/paternity leave
• As much freedom and independence as you earn, and a chance to grow rapidly as the company does.
• Flexi and hybrid working
• Company's office in Paddington - easy commute and comfortable surroundings
• We’ll equip you with laptop and any necessary gear.
• Motivated, highly functioning, multi-disciplinary team

Interview Process

• Stage 1 - 30min interview to understand technical fit
• Stage 2 - 1h technical deep dive
• Stage 3 - 30min interview at the company offices
• Offer