Data Scientist

Description

The team is cross-functional and prepares data and supports modeling for product development and manufacturing science work.

In the product development labs, you would work with modeling experts and the digital group to pull data from source systems and data lakes and run statistical, hybrid and mechanistic models.

The goal is a lab-in-the-loop setup in which data collection through model execution is automated end to end and open to all lab scientists.

The role also offers a chance to learn bioprocess data and multivariate, hybrid and machine learning modeling, with a focus on quality and productivity.

The company develops medicines in immunology, oncology and neuroscience, and also offers aesthetics products.

Responsibilities

• Work with manufacturing sciences to compile, clean and engineer features from the same laboratory and commercial datasets for multivariate and hybrid digital twin process models.
• Work with the digital group to turn proven proofs of concept into end-to-end data pipelines, products and models.
• Show initiative and creativity in research and development work.
• Carry out laboratory research or method development on your own, needing little direction or contact with your supervisor.
• Draw conclusions and plan follow-up experiments from multidisciplinary data.
• Start new lines of investigation that are scientifically sound and can feed directly into a research or development program.
• Serve as a lead author on publications, presentations and regulatory documents, or as lead inventor on patents.
• Apply strong skills across a broad range of relevant technologies.
• Follow company standards on code of conduct, safety, material handling, controlled and radioactive compounds, GxP compliance and animal care where relevant.

Requirements

• Bachelor's degree or equivalent, typically with 10 years of experience; Master's degree or equivalent, typically with 8 years of experience; or PhD with no experience required.
• Solid theoretical and practical understanding of your scientific discipline.
• Prior experience in biotech or pharmaceuticals.
• Preferred qualifications:
• Preferred: Master's degree in data engineering, data science or a related field.
• Preferred: Strong programming experience, including Python and SQL, among others.
• Preferred: Experience with standard cloud-based data lake infrastructure.
• Preferred: Experience with source code management tools such as GitHub.
• Preferred: Familiarity with data pipeline tools such as KNIME and dbt.
• Preferred: Familiarity with model management and pipeline tools such as MLflow and Databricks.
• Preferred: Familiarity with ServiceNow, or willingness to learn it, and support for application owner and access reviews for data and modeling capabilities.
• Preferred: Experience with biotech data systems such as AVEVA PI, LIMS, ELN, MES and ERP.
• Preferred: Experience with laboratory automation and data.
• Preferred: Some experience with BI tools such as Spotfire and Power BI.
• Preferred: Experience with SIMCA, JMP or hybrid modeling.
• Preferred: Interest in learning, or experience with, process, statistical, hybrid, mechanistic and/or machine learning models.

Conditions

Base pay falls within a range set for the job grade, and the actual figure depends on factors such as location; it may be above or below the posted range, and the range may change.

Open only to applicants in the US and Puerto Rico.

Any bonus, incentive, benefit or other compensation remains at the company's sole discretion until paid and may change, consistent with applicable law.

The company is an equal opportunity employer covering veterans and people with disabilities.

Benefits

• Paid time off covering vacation, holidays and sick leave.
• Medical, dental and vision insurance.
• 401(k) for eligible employees.
• Eligibility for short-term incentive programs.