About the Role
About SupplyWhySupplyWhy is building the future of autonomous supply chain planning. We deploy AI systems that replace fragile, spreadsheet-based processes with resilient, self-healing supply chains capable of making real-time decisions at enterprise scale. Starting with the automotive industry, we're tackling inefficiencies in one of the world's most complex supply chain ecosystems.Our platform combines probabilistic forecasting, agentic AI, and deep supply chain domain expertise. We work with Fortune 500 manufacturers to transform how they plan, forecast, and respond to disruptions.
About the RoleAs a Data Scientist on our Core ML team, you'll own and deliver key components of our forecasting and ML systems. This is hands-on technical work: time-series modeling, feature engineering, model productization, and MLOps. You'll work directly with the Lead DS to execute on our product roadmap for enterprise customers.We're looking for someone who can operate independently - scoping work, making technical decisions, and delivering production-ready code with minimal oversight. You'll also help mentor junior team members as we grow.
What You Will Do
• Own end-to-end development of time-series forecasting models (statistical and ML-based) for demand prediction
• Design and implement feature engineering pipelines for structured and unstructured data
• Build anomaly detection systems for data quality and demand signal monitoring
• Architect and deliver production-quality code: config-driven, testable, scalable Python modules
• Implement model ensembling, hierarchical reconciliation, and automated model selection
• Drive MLOps infrastructure: experiment tracking, CI/CD, model registry
• Make technical decisions on model architecture, data pipelines, and system design
• Mentor junior team members and contribute to technical standards
• Collaborate with the team using AI-assisted development tools (Cursor, Claude Code)
Must Have
• Bachelor's or Master's in Computer Science, Statistics, Mathematics, or related quantitative field
• 2-4 years of experience in applied ML/DS roles with production deployments
• Strong Python skills with experience writing production-quality, maintainable code
• Hands-on experience with time-series forecasting or demand prediction
• Proficiency with ML frameworks (scikit-learn, CatBoost/XGBoost, or similar)
• Solid understanding of statistical concepts: probability distributions, hypothesis testing, regression, stationarity
• Experience with SQL and data manipulation at scale (pandas, numpy, SQL)
• Track record of delivering ML projects from prototype to production
• Ability to work independently, make technical decisions, and communicate trade-offs
• Comfortable in a remote-first environment with async collaboration
Nice to Have
• Experience with probabilistic forecasting, quantile regression, or uncertainty estimation
• Hands-on exposure to MLOps tools (MLflow, DVC, Airflow, Kubeflow, or similar)
• Background in supply chain, manufacturing, logistics, or enterprise operations
• Experience with hierarchical/grouped time-series methods or forecast reconciliation
• Familiarity with LLMs and AI-assisted development workflows
• Experience mentoring junior engineers or data scientists
Why Join Us
• Production ML at scale: Your models power forecasts for Fortune 500 manufacturers
• Technical ownership: Own projects end-to-end, make architectural decisions
• Depth over breadth: Specialize in time-series, forecasting, and ML systems - not generalist work
• AI-native workflow: Heavy use of AI tools (Claude, Cursor) - work at the frontier of modern development
• High-trust environment: We hire good people and give them autonomy
• Shape the team: Early hire = influence on technical direction and culture as we grow
• Remote-first: Flexible work from anywhere