Smartsheet Senior Data Scientist II at Smartsheet building ML models and AI sub-agents to drive growth and retention across the customer lifecycle. Responsible for end-to-end model development and production deployment.
Responsibilities
Design and ship AI sub-agents that act across the customer lifecycle, combining predictive models, retrieved context, and LLM reasoning to recommend or take action
Build the predictive and prescriptive models that power those sub-agents churn risk, growth, adoption trajectories, account health scoring, and similar lifecycle problems
Develop the data foundations and knowledge layer those sub-agents reason over, applying responsible aggregation and privacy-aware design
Design the tools, retrieval, and grounding strategies each sub-agent uses; decide when a sub-agent should act, recommend, defer, or escalate
Build the evaluation harnesses that determine when a sub-agent is good enough to ship and that catch regressions in production
Define metrics and experimentation strategy for sub-agent rollouts; measure real customer impact, not just offline accuracy or eval scores
Partner with Product, Engineering, and Applied AI teams from problem framing through production deployment
Drive a data and modeling culture within Product and Engineering, and mentor other data scientists on the team
Understand our customer needs and design metrics to analyze how our customers are using product and optimize products and features
Conduct experiments, causal studies and A/B tests to measure the impact of product changes
Qualification
Proficient in SQL and PythonA pragmatic production barCurrent US Perks & Benefits
Required
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
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
Strong grasp of causal inference for intervention design and lifecycle modeling: uplift modeling, difference-in-differences, propensity scoring, and synthetic control
Solid foundation in statistics and experimental design: hypothesis testing, power analysis, multiple comparisons, sequential testing, and quasi-experimental methods
Hands-on experience taking LLM- and agent-based systems to production: tool use, retrieval, multi-step reasoning, evaluation, and guardrails
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
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)
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)
A pragmatic production bar: latency, cost, monitoring, drift, hallucination, and what happens when the model or sub-agent is wrong
Strong track record of forming effective cross-functional partnerships and communicating analysis clearly to technical and executive audiences
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