Data Scientist
Core
Prepare data and enable modeling activities to streamline and automate laboratory data and modeling in a 'Lab-in-the-Loop' environment for Product Development and Manufacturing Sciences.
Role type
Data Scientist (Bioprocess & Modeling)
Builds
End-to-end data pipelines, products, and models for statistical, hybrid, and mechanistic models.
Domain
Biopharmaceuticals / Bioprocess
Deliverable
production ML models
Required skills
Data cleaning and feature engineering, Multivariate and hybrid modeling, Machine learning, Python, SQL, Cloud-based data lake infrastructure, Source code management (GitHub), Data pipeline tools (KNime, dbt), Model management tools (ML Flow, DataBricks), Biotech data systems (AVEVA PI, LIMS, ELN, MES, ERP), Laboratory automation, BI tools (Spotfire, PowerBI), SIMCA, JMP.
Preferred skills
Masters in Data Engineering or Data Science, Experience with process/statistical/mechanistic models, Experience in biotech or pharmaceuticals.
Responsibilities
Compile, clean, and feature engineer laboratory and commercial data sets for 'Digital Twin' process models; Partner with the Digital organization to deliver end-to-end data pipelines, products, and models from proofs of concept; Formulate conclusions and design follow-on experiments based on multidisciplinary data; Demonstrate scientific initiative and creativity in research or development activities.
Seniority
Mid-Senior (8-10 years experience) (via careerplan.io/jobs/3743990015808116-data-scientist-at-abbvie)