Lead Data Scientist

The candidate will have responsibilities across the following functions:

AI/ML Model Development:

• Design and own models for demand forecasting, price/promo elasticity, forecast-driver attribution, time-series anomaly detection, and constrained optimization/simulation.
• Apply the right tool for the problem: gradient boosting, deep learning, probabilistic and hierarchical forecasting, causal inference, Bayesian methods, MILP; reinforcement learning and GenAI/foundation-model applications are a plus.
• Own model quality end-to-end accuracy, bias, and MAPE against business-defined targets, not just offline metrics.

Product and Platform Contribution:

• Contribute to the architecture of a multi-tenant, explainable, configurable enterprise AI SaaS platform.
• Move research into production fast; build reusable frameworks for feature engineering, validation, and experimentation, and support the models you ship through their full lifecycle.
• Work across large, messy, real-world data: transactional systems, syndicated/external data (e. g., Circana/Nielsen-type sources), and digital signals.

Customer and Consulting Engagement:

• Sit directly with customers to understand their forecasting and RGM challenges and turn them into scoped, deliverable AI solutions.
• Present model logic, trade-offs, and roadmap to both technical and executive audiences.
• This role requires the ability to defend a model's assumptions in a room that isn't full of data scientists.
• Make build-vs-buy calls on modelling approaches and GenAI/LLM tooling alongside Product and Engineering.

Team Leadership:

• Lead and mentor a small team of data scientists/ML engineers; raise the bar on ML system design, MLOps, experiment tracking, and AI governance.
• Partner with Product, Engineering, and Customer Success to define the AI roadmap and success criteria for forecasting capabilities.

Requirements:

• 8-10 years in Data Science/ML roles, with meaningful time in enterprise SaaS and/or CPG/Retail forecasting or Revenue Growth Management.
• At least one complete AI/ML product development lifecycle from early build through to a scaled, customer-facing product, not just research or POC work.
• Direct experience with demand forecasting, price elasticity, or related time-series/causal modelling problems at production scale.
• Strong Python ecosystem fluency: Pandas, NumPy, Scikit-learn, PyTorch/TensorFlow, Prophet or equivalent.
• Comfort with cloud platforms (Azure/GCP) and building distributed, production-grade pipelines.
• Demonstrated ability to work directly with customers or business stakeholders translating ambiguous problems into technical scope.
• Bachelor's/Master's/PhD in Computer Science, Statistics, Mathematics, Economics, Operations Research, or related field.

Nice to Have:

• Experience in AI/tech consulting engagements for CPG or retail clients.
• Exposure to GenAI/LLM-based applications and AI agents.
• MLOps tooling, orchestration systems, real-time inference pipelines.
• Patents, published research, or hackathon/competition track record.