Lead Data Scientist – Virtual Models
Core
Lead a new programme to develop virtual pharmacology models using biological datasets to assess molecule efficacy and support screening activities.
Role type
Senior individual contributor data scientist (virtual models)
Builds
Production-ready machine learning models and data pipelines for virtual pharmacology
Domain
Life Sciences / Biostatistics / Machine Learning
Deliverable
production ML models
Required skills
PhD in data science/biostatistics/bioinformatics/ML, 8-10 years experience, complex biological datasets, data pipeline construction, data quality assessment, experimental design, scientific validation, reproducible code, Python/R, cloud platforms (Snowflake), MLOps
Preferred skills
Client presentation, entrepreneurial mindset, team leadership
Technologies
Python, R, Snowflake, MLOps
Responsibilities
Assess proposals and underlying data quality, recommend high-potential models, build data pipelines, develop ML models and PoCs, define experiments with lab scientists, establish validation criteria, iterate models, ensure reproducibility, present results to diverse audiences, prepare for commercialization, protect IP
Seniority
Senior, hands-on IC with potential to lead team
