Lead Data Scientist - US Remote

Job Responsibilities

Lead complex data science and machine learning initiatives supporting supply chain, manufacturing operations, capacity planning, demand forecasting, and operational decision-making.

Design, develop, and own advanced ML solutions — including predictive models, time-series forecasting, optimization, and decision-support systems — scoped to supply chain and manufacturing use cases.

Build, train, evaluate, and interpret machine learning models (regression, classification, clustering, forecasting) to quantify supply chain drivers, surface optimization opportunities, and improve operational outcomes.

Develop and operationalize analytics and ML solutions using Databricks (Python / SQL / PySpark) for large-scale data processing, model development, and experimentation.

Design and build multi-agent AI systems — including orchestrator-executor architectures, tool-calling agents, and RAG-based decision support — using frameworks such as Azure AI Foundry, AutoGen, Semantic Kernel, or LangChain/LangGraph.

Implement and extend solutions using the MCP to enable AI agents to access and act on enterprise data systems in supply chain and manufacturing contexts.

Apply data science best practices including feature engineering, model validation, performance monitoring, reproducibility, and documentation.

Partner with Supply Chain & Procurement leadership, Manufacturing Ops, Process Engineering, Demand Planning, and IT to translate ambiguous business problems into structured ML and AI approaches.

Develop and maintain self-service, automated, and AI-enabled analytics workflows that reduce manual effort and improve decision latency.

Leverage Azure AI Foundry, Microsoft Copilot Studio, and Microsoft 365 Copilot extensibility to prototype and deploy AI-powered analytics and agent-based decision-support tools.

Produce executive-ready insights through clear storytelling, visualizations, and recommendations using Power BI or embedded analytics.

Set technical direction, establish reusable ML and AI frameworks, and mentor junior and mid-level data scientists across the team.

Ensure high standards of data quality, governance, model validation, and explainability.

Minimum Qualifications

• Education & Experience (one of the following):
  • Master’s degree in Statistics, Mathematics, Industrial Engineering, Data Science, Computer Science, Engineering, or a related quantitative field with 5+ years of relevant data science/analytics experience, OR
  • Bachelor’s degree in the same or related fields with 8+ years of relevant data science / analytics experience.
• Demonstrated track record delivering advanced ML and data science solutions in supply chain, manufacturing, or industrial domains.
• Strong hands-on experience with machine learning and statistical modeling — development, interpretation, and operational business application.
• Strong proficiency in Databricks (Python, SQL, PySpark, Delta Lake).
• Hands-on experience with the MCP — building or consuming MCP servers/clients to connect AI agents to enterprise data systems, APIs, or ERP modules.
• Hands-on experience with multi-agent system design — architecting multi-agent systems using AutoGen, Semantic Kernel, LangChain/LangGraph, or Azure AI Agent Service; orchestrator-executor patterns, tool calling, memory management, and agent coordination.
• Compulsory — must have hands-on experience with one or more of the following:
• Azure AI Foundry
• Microsoft Copilot Studio
• Microsoft 365 Copilot extensibility
• Microsoft Power Platform (Power Automate, Power BI)
• Ability to translate complex business problems into ML / AI solutions and communicate findings to both technical and executive audiences.
• Strong stakeholder management and cross-functional collaboration skills.

Preferred Qualifications

• Experience operationalizing ML models into production in supply chain or manufacturing environments.
• Familiarity with SAP ECC / S/4HANA supply chain and manufacturing modules (MM, PP, PM, SD).
• Strong Power BI experience — semantic modeling, performance optimization, executive dashboard design.
• Exposure to MLOps on Azure (Azure ML, MLflow, Databricks Asset Bundles, CI/CD for analytics artifacts).
• Experience designing operational KPI frameworks (MAPE, OTIF, service level, OEE, downtime).
• Experience with statistical / simulation methods (Monte Carlo, scenario analysis, sensitivity analysis) applied to operations and supply chain.
• Familiarity with Palantir Foundry (pipelines, ontology, Workshop, AIP).
• Proven experience mentoring data scientists or leading end-to-end analytics initiatives.
• Familiarity with cloud-native data architectures and governed data platforms.