Senior Data Scientist, CMC

Praxis Precision Medicines, Inc.

1d•$150,000 - $170,000•Remote

About The Position

Praxis is seeking a Senior Data Scientist to build and deploy the models, data products, and digital tools that help us develop drug substance and drug product processes, as well as the packaging and labeling that gets them to patients quickly and correctly the first time. Working within CMC alongside Engineering, Process Chemistry, Formulation, Analytical Development, Quality, Data Science, and external CDMOs, you will turn process and experimental data into actionable insight and phase-appropriate decisions across small molecule and oligonucleotide programs. This is a hands-on, high-ownership role for a data scientist or process engineer who thrives on open-ended problems. You will combine process knowledge with modern data science and AI to improve technology transfer timelines, strengthen process understanding, and make CMC data FAIR, traceable, and reusable across the organization.

Requirements

Master’s degree in Chemical Engineering, Pharmaceutical Sciences, Data Science, or a related scientific or engineering field, with demonstrated application of data science to process development; Bachelor’s degree with equivalent experience will be considered.
5+ years of relevant experience in biotech/pharma process development, process engineering, or data science, ideally supporting drug substance and/or drug product development or technology transfer.
Experience with process modeling, DoE, statistical analysis, and data-driven decision-making; exposure to packaging and labeling operations is a plus.
Strong hands-on skills in Python and SQL, with experience using Databricks or comparable data platforms and BI/visualization tools such as Power BI, Tableau, or Spotfire.
Working knowledge of cGMP, ALCOA+, CMC regulatory expectations, and GxP-validated computerized systems; experience supporting regulatory filings is a plus.
Demonstrated ability to solve ambiguous problems, communicate complex ideas clearly, work with self-direction, and build trusted relationships across functions.
Brings intellectual curiosity, creativity, innovation, organization, attention to detail, and a strong bias toward high-quality results. Thrives in an agile, entrepreneurial environment and is willing to both teach and learn.

Nice To Haves

Experience developing AI/ML applications and integrating AI-enabled tools into scientific or business workflows preferred.
Experience working with CDMOs/CROs, external data flows, Agile ways of working, digital product ownership, or change management preferred.

Responsibilities

Lead the development, validation, and deployment of mechanistic, hybrid, and data-driven models supporting drug substance, drug product, packaging, and labeling processes, technology transfer, and manufacturing.
Partner with technical teams and CDMOs to translate DoE, PAT, IPC, batch record, and other process data into predictive models and analytics that inform process understanding, control strategy, risk assessment, and phase-appropriate decisions.
Build analytics for drug product unit operations such as blending, granulation, compression, coating, and fill/finish, as well as packaging and labeling operations, including yield, throughput, readiness, and supply-chain scenario analysis.
Develop and maintain pipelines and FAIR data products that integrate internal and CRO/CDMO data into traceable, reusable datasets within Databricks and related platforms. Develop dashboards and visualizations that make process performance, campaign comparisons, and technology-transfer readiness clear to technical and executive audiences.
Serve as digital product owner for process modeling and technology-transfer analytics, defining priorities, driving adoption, and applying AI/ML—including agentic workflows and LLM-based tools—to accelerate CMC data review, knowledge capture, and routine analytical work with appropriate validation and data-integrity controls.
Use forecasting, scenario analysis, and cost-benefit analysis to improve right-first-time execution and shorten technology-transfer timelines. Present recommendations to stakeholders, contribute to CMC data science strategy and regulatory filings, and mentor colleagues in data science and modeling practices.