Senior Data Scientist

Join Smartsheet as a Senior Data Scientist II, where you will build ML models and AI sub-agents to drive growth, monetization, efficiency, and retention across the customer lifecycle. You will work end-to-end, framing problems, building models, designing sub-agents, and shipping them into production for millions of users. You will primarily collaborate with Product and Engineering and be part of Smartsheet's Business Intelligence team.

• Concevoir et expédier des sous-agents d'IA qui agissent tout au long du cycle de vie du client, en combinant des modèles prédictifs, un contexte récupéré et un raisonnement LLM.
• Construire des modèles prédictifs et prescriptifs qui alimentent ces sous-agents, en abordant des problèmes tels que le risque de désabonnement, la croissance et l'adoption.
• Développer les fondations de données et la couche de connaissance sur lesquelles ces sous-agents raisonnent, en appliquant une agrégation responsable et un design respectueux de la vie privée.
• Deep applied ML expertise across both traditional ML and deep learning: gradient boosting, regularized linear models, transformer-based sequence models, foundation model embeddings, causal ML, contextual bandits, and offline RL
• Proficient in SQL and Python; comfort with ML/LLM tooling at scale (Spark, Databricks, Snowflake, or equivalents), ML frameworks (PyTorch, scikit-learn, XGBoost/LightGBM), and visualization tools (Tableau or similar)
• Strong grasp of causal inference for intervention design and lifecycle modeling: uplift modeling, difference-in-differences, propensity scoring, and synthetic control
• Experience modeling the customer lifecycle — churn, expansion, adoption, plan health, lead/account scoring — and business fluency in the SaaS metrics that drive it (NRR, GRR, ARR, and cohort economics)
• Bachelor’s degree and 8+ years of experience (or 10+ years of experience); advanced degree in a quantitative field (Statistics, CS, ML, Economics, Operations Research, or similar) preferred
• Hands-on experience taking LLM- and agent-based systems to production: tool use, retrieval, multi-step reasoning, evaluation, and guardrails
• Solid foundation in statistics and experimental design: hypothesis testing, power analysis, multiple comparisons, sequential testing, and quasi-experimental methods
• Strong track record of forming effective cross-functional partnerships and communicating analysis clearly to technical and executive audiences
• Experience operating ML in production — feature engineering and pipelines, model monitoring, drift detection, retraining cadence, and the trade-offs between batch and real-time serving
• A pragmatic production bar: latency, cost, monitoring, drift, hallucination, and what happens when the model or sub-agent is wrong
• Ability to research and learn new technologies, tools, and methodologies, and to thrive in a dynamic environment — finding opportunities and executing in both independent and collaborative environments