Data Scientist

At Nerd Wallet, we’re on a mission to bring clarity to all of life’s financial decisions and every great mission needs a team of exceptional Nerds. We’ve built an inclusive, flexible, and candid culture where you’re empowered to grow, take smart risks, and be unapologetically yourself (cape optional). Whether remote or in-office, we support how you thrive best. We invest in your well-being, development, and ability to make an impact because when one Nerd levels up, we all do.

Staff Data Scientist leads machine learning and decisioning systems powering personalization, lifetime value (LTV) prediction, and real-time commercial optimization across our marketplaces. This role is responsible for designing and scaling causal measurement and personalization systems that determine how we serve users while balancing customer value, partner economics, and long‑term trust. As a senior individual contributor, you will drive high‑impact modeling initiatives and shape the technical direction of data science across the organization.

You are a technical expert and strategic partner who operates with significant autonomy and influence. As a Staff Data Scientist, you set the standard for scientific rigor, mentor senior ICs, and guide cross‑functional teams without formal authority. You partner closely with Product, Engineering, Marketing, and Finance to align data science investments with business strategy, while shaping long‑term vision for AI‑driven personalization and marketplace optimization.

This role reports to the VP, Data & Analytics.

• Lead the design and implementation of causal inference frameworks (e.g., uplift modeling, DML, IVs, DiD, synthetic control) to measure true incremental impact across personalization, marketing, and lifecycle interventions

• Establish and standardize methodologies for incrementality, experimentation, and measurement across channels and product surfaces

• Build and scale LTV models (user‑level and cohort‑based), including churn‑adjusted and horizon‑specific approaches, for real‑time decisioning

• Develop and deploy personalization models that influence ranking, offer selection, content sequencing, and monetization strategies at the moment of user intent

• Ship production‑grade machine learning models that directly drive revenue outcomes, including marketplace optimization, partner routing, and budget allocation

• Translate predictive outputs (e.g., conversion propensity, incremental CPA, expected LTV) into decision‑ready signals for real‑time systems

• Partner with Data Engineering and Platform teams to define data instrumentation, feature stores (batch and streaming), and model monitoring frameworks (drift, bias, stability)

• Influence architectural decisions across modern data and ML platforms (e.g., Snowflake, Databricks, Spark, real‑time inference systems)

• Provide technical leadership across teams by setting best practices for experimentation, modeling, code quality, and reproducibility

• Mentor and develop senior and mid‑level data scientists, raising the overall technical bar across the organization

• Communicate complex analytical insights and trade‑offs to executive stakeholders, translating findings into actionable business strategies

• Shape long‑term strategy for personalization, experimentation, and AI‑driven growth at Nerd Wallet

• 8+ years of experience in applied machine learning, causal inference, experimentation, or related quantitative fields

• Deep expertise in causal inference methodologies (e.g., uplift modeling, doubly robust learners, instrumental variables, difference‑in‑differences, synthetic control, Bayesian time series)

• Proven experience building and operationalizing LTV models for real‑time or near‑real‑time applications

• Strong software engineering and production ML experience, including Python (pandas, numpy, scikit‑learn, LightGBM/XGBoost) and PySpark, Advanced SQL

• Experience with distributed systems and modern data platforms (e.g., Snowflake, Databricks, Spark, AWS/GCP/Azure), version control and ML lifecycle tools (e.g., Git, MLflow)

• Hands‑on experience with experimentation frameworks, A/B testing, and statistical diagnostics (e.g.,…