Data Scientist - Advanced Manufacturing Technologies (AMT)

Responsibilities

• Independently design, create, validate, and continually refine scalable multivariate models using machine learning algorithms such as gradient boosting, partial least squares (PLS), support vector machines, and neural networks along with advanced feature engineering, validation, and explainability techniques to ensure model robustness and interpretability while managing high dimensional data sets.
• Leverage AI foundational models, pipelines, and agentic techniques to extract insight, structured results, and recommendations from large and diverse chemical knowledge bases and generate analyses.
• Develop and apply modelling algorithms using chemical, materials, and biologic data sets.
• Act as a subject-matter expert on AI, Machine Learning, and data science on cross-functional projects, including the technical design of proposals and plans of research.
• Develop and deploy scalable AL/ML tools for client and internal use within the AMT team to improve efficiency and quality of complex, technical and economic analyses.
• Design and implement models within key AMT areas of interest including: Pharmaceutical supply chain and chemical synthesis; Novel drug manufacturing technologies such as flow chemistry, process analytical technologies (PAT), pharmaceutical 3D printing; Environmental impact and total lifecycle analysis of pharmaceutical manufacturing and optimization against environmental impacts, cost of production.
• Maintain primary ownership over model requirements, specification, design, and implementation in one of the three key AMT areas of interest.
• Ensure all work is done on time, meets client expectations, and exemplifies the trust, quality, and reliability expected from a USP solution.

Qualifications

• Demonstrated understanding of USP's mission, commitment to excellence through inclusive and equitable behaviors and practices, ability to quickly build credibility with stakeholders, and desire to affect change and drive public health impact.
• Bachelor’s Degree and five (5) years of relevant experience; master’s degree and three (3) years of relevant experience; or a Ph.D. and one (1) year of relevant experience required.
• Programming and computational abilities in data science languages and frameworks (e.g., Python—Pandas, scikit-learn, Matplotlib, TensorFlow, PyTorch, LangChain; R; MATLAB;).
• Demonstrated experience with cheminformatics and retrosynthetic frameworks such as RDKit, SynPlanner, and AIZynthFinder.
• Demonstrated experience applying machine learning and statistical techniques to complex systems such as pre-processing, classification, regression, clustering, dimensionality reduction, anomaly detection, and model selection.
• Experience following good software engineering practices, designing scalable solutions, validating pipelines, and deploying solutions into production.
• Experience deploying to cloud environments and services such as AWS, Azure, or Google Cloud.
• Working knowledge of organic chemistry, chemical synthesis, the pharmaceutical industry, and manufacturing.
• Strong analytical reasoning, critical thinking, and troubleshooting ability.
• Ability to engage productively with both internal and external stakeholders and oversee vendors.
• High attention to detail and integrity.
• Initiative to solve problems and develop solutions on a deadline.
• Solid communications skills – both written and oral.

Skills

• Data Science
• Machine Learning
• Python
• R
• Matlab
• Cheminformatics
• Retrosynthetic Analysis
• Cloud Computing
• Organic Chemistry
• Chemical Synthesis

Pay

Base Salary Range: USD $89,816.00 – $113,450.00 annually.

Schedule

Full-Time