Data Scientist, Sr. Specialist, Supply Risk Analytics

Position Summary

The PDS BI&T team (Product Development & Supply Business Insights & Technology) partners with the BMS PDS organization to answer key business questions that drive supply strategy and operational decisions using data science, machine learning and Generative AI. The Data Scientist, Sr. Specialist joins the Supply Risk Analytics team, reporting into the Risk Analytics lead, and contributes to AI-enabled analytics that quantify, monitor and mitigate risk across the BMS supply network and support network strategic decisions. This is a hands-on, early-career role with a clear growth path: you will work alongside experienced data scientists and engineers, take ownership of well-scoped pieces of larger solutions, and steadily build depth in supply risk analytics, probabilistic modeling and applied Generative AI. AI-assisted development is part of how the team works every day, and you will use Claude Code to build, test, document and refactor code from your first weeks. The successful candidate has a quantitative background, solid Python and SQL fundamentals, curiosity about how AI is changing analytics work, and the communication skills to explain results to non-technical partners. Deep supply chain or life sciences knowledge is not required. We will teach you the domain.

What You Will Do

AI-Enabled Supply Risk Modeling

• Contribute to machine learning and probabilistic models, including Monte Carlo simulation, that quantify supply risk such as inventory-at-risk, service level exposure and supplier disruption scenarios, under the guidance of senior team members.
• Help build Generative AI and agentic features using Claude: LLM-generated risk narratives, intelligent alerts, natural-language interfaces to risk data, and AI agents that automate scenario analysis.
• Develop and maintain forecasting and anomaly detection components that produce risk scores and early-warning signals, and help translate outputs into clear recommendations.
• Build interactive front-ends (e.g., Streamlit, React) that put risk models in the hands of business users, and create agentic workflows and reporting automations that replace manual, recurring analysis.
• Balance quick-turn ad-hoc analyses for urgent business questions with long-running digital product development delivered in an agile setup of sprints, backlog refinement and retrospectives.
• Document assumptions, data, methodology and validation results, applying BMS responsible AI, data privacy and quality practices.

Business Collaboration

• Partner with Supply Chain, Business Continuity Management, Quality and Procurement stakeholders to understand priority risk questions and help frame them as analytic problems that support network strategic decisions.
• Support demos and walkthroughs of results for business partners, growing toward presenting trade-offs to leaders independently.
• Collaborate day to day with a cross-functional team of data scientists, engineers and business partners spread across the US, Europe and Asia, working effectively across time zones.

Engineering & Technology

• Use Claude Code daily as a core development tool for scaffolding pipelines and models, generating tests, and refactoring and documenting code, while learning to apply sound engineering judgment and peer review.
• Work with Data Engineering to define data requirements and build pipelines on Databricks and AWS Glue, ensuring model inputs are reliable and traceable.
• Develop and deploy AI applications within BMS’s enterprise AI platform, learning to work in large, shared GitHub codebases with branching, code review, release and CI/CD conventions.
• Write clean, reusable, well-tested Python and SQL, contribute to shared prompt libraries and components, and participate in agile ceremonies.
• Actively seek feedback and coaching from the Risk Analytics lead and senior peers to grow in both data science and applied AI development.

Qualifications & Experience

Required Qualifications

• B.S. or M.S. in a relevant life sciences, informatics, data, or technical discipline (e.g., data science, statistics, operations research, engineering, computer science); advanced degree a plus.
• 2 - 4 years of experience in IT, informatics, data analysis, business analysis, or a scientific data-focused role; relevant graduate research or internship experience may be considered.
• Working proficiency in Python and SQL for data manipulation, analysis and modeling, with a solid grounding in statistics and probability.
• Some hands-on exposure to machine learning or Generative AI through work, coursework or personal projects, and a strong interest in AI-assisted development tools such as Claude Code.
• Clear written and verbal communication and a collaborative, learning-oriented mindset, comfortable working in a global team across continents and time zones.

Preferred Qualifications

• Experience with Databricks (Spark, Delta Lake, notebooks) or AWS data services such as AWS Glue.
• Exposure to LLM application development (prompt engineering, RAG, LangChain/LangGraph, Anthropic Claude) or to AI agent development.
• Familiarity with simulation or decision analysis under uncertainty (e.g., Monte Carlo methods).
• Experience contributing to shared GitHub repositories, CI/CD tooling (e.g., GitHub Actions) and agile tools such as Jira.
• Experience building analytic front-ends or visualizations (e.g., React, Streamlit).
• Exposure to pharmaceutical supply chain, business continuity management or another regulated environment.