Data Scientist

Alldus International Consulting Ltd; Dublin; On-site; EUR 60,000 - 90,000; Full time

Job summary

Alldus International Consulting Ltd seeks a Data Scientist in Dublin to support clinical trial feasibility, site selection, and enrollment forecasting. The role involves building predictive models and delivering actionable insights for study planning and activation.

The candidate will design and evaluate regression, classification, and ranking models, engineer features from clinical datasets, and communicate complex results to sponsors and stakeholders.

Qualifications

• Experience in life sciences or clinical research environments is desirable.
• Strong Python proficiency and ML framework experience.
• Experience with clinical trial data and feasibility analysis is preferred.

Responsibilities

• Develop predictive models for clinical trial feasibility, including site and country selection.
• Design regression, classification and ranking models to forecast site performance and enrollment.
• Apply modeling evaluation, calibration, and validation techniques for operational use.
• Engineer features from diverse clinical and operational datasets.
• Communicate outputs and recommendations to sponsors and non-technical stakeholders.

Skills

Data science

Machine learning

Python

Feature engineering

Model evaluation

Causal inference

Data wrangling

MLOps

Tools

Azure Machine Learning

MLflow

Delta Lake

Lakehouse

Big data tooling

Job description

Our client, a leading healthcare organisation, is hiring a Data Scientist to join their team in Dublin on either a full-time or contract basis. The successful candidate will support clinical trial feasibility, study start-up, site selection and patient identification, developing predictive models to forecast trial performance and generate insights that help improve study planning, enrollment and overall outcomes.

Responsibilities

• Develop predictive models to support clinical trial feasibility, including country and site selection, enrollment forecasting, study start-up and patient identification.
• Design, build and assess regression, classification and ranking models to predict site performance, enrollment potential and trial outcomes.
• Apply effective model evaluation, validation and calibration techniques to ensure models are accurate, reliable and suitable for operational decision-making.
• Create and engineer features from diverse clinical and operational datasets, including site performance, investigator and KOL, epidemiological, patient population, competitive trial, CTMS and EDC data.
• Integrate and reconcile data across sites, investigators, protocols, studies and patient populations, resolving inconsistent identifiers across multiple systems and sources.
• Use causal inference techniques, including uplift modelling, counterfactual analysis and intervention effect estimation, to understand the factors influencing enrollment and study activation.
• Assess the potential impact of interventions such as adding or replacing sites, modifying patient eligibility criteria and adjusting site support strategies.
• Build scenario modelling and simulation capabilities to evaluate different site mixes, patient populations, enrollment assumptions and activation timelines.
• Support the development, deployment, monitoring and evaluation of models within a cloud-based MLOps environment.
• Communicate complex analytical outputs, including site rankings, enrollment forecasts and scenario analyses, as clear, actionable recommendations for sponsors and non-technical stakeholders.

Skillset

• Strong experience in data science, machine learning or advanced analytics, ideally within life sciences, pharmaceuticals, biotechnology, CROs or clinical research environments.
• Practical experience working with clinical trial feasibility, site selection, study start-up, patient identification or clinical development data is highly desirable.
• Strong proficiency in Python and commonly used data science and machine learning frameworks and libraries.
• Hands-on experience building and applying regression, classification and ranking models.
• Solid understanding of model evaluation, validation, calibration and performance measurement.
• Experience combining, transforming and engineering features from large, complex and varied datasets.
• Experience with entity resolution and master data linkage, particularly across sites, investigators, studies, protocols and related clinical data.
• Understanding of causal inference techniques, including uplift modelling, counterfactual analysis and treatment effect estimation.
• Familiarity with Azure Machine Learning, MLflow or similar cloud-based MLOps platforms.
• Experience working with lakehouse, Delta Lake or comparable modern data architectures.