Staff Data Scientist

The Senior Data Scientist will be a core contributor within the India COE data science practice, responsible for independently designing and executing statistical analyses, developing predictive models, and translating complex data into clear, defensible insights that inform business decision-making. This role partners closely with business partners to convert business questions into well-scoped analytical problems and works with Data Engineering, Analytics Engineering, and AI Engineering to ensure outputs are reproducible, governed, and actionable. The Senior Data Scientist is expected to execute end-to-end analytical work with limited oversight while contributing to shared methods, reusable code, and model documentation standards.

The candidate will have responsibilities across the following functions:

Statistical Analysis and Quantitative Methods:

• Design and execute statistical analyses in response to business questions, including hypothesis testing, significance testing, power analysis, and confidence interval estimation.
• Apply causal inference techniques to observational data where controlled experiments are not feasible, including difference-in-differences, regression discontinuity, propensity score matching, and synthetic control.
• Develop and execute A/B and multivariate testing frameworks: randomization design, sample size calculation, holdout group construction, and interpretation of results with appropriate uncertainty quantification.
• Conduct time-series analysis including decomposition, forecasting, and anomaly detection across business and operational metrics.
• Apply survival analysis and event-based modeling to understand time-to-event patterns and duration dependencies in the data.
• Build segmentation and clustering solutions that identify meaningful structure in complex datasets and support strategic targeting and prioritization.
• Document all analytical work with clarity: methodology, assumptions, limitations, sensitivity analyses, and confidence in conclusions suitable for peer review.

Predictive Modeling and Machine Learning:

• Develop, validate, and monitor predictive models including propensity scoring, churn modeling, demand forecasting, and anomaly detection grounded in statistical best practices.
• Apply feature engineering, model selection, regularization, and cross-validation techniques to build models that generalize reliably beyond training data.
• Evaluate model performance using appropriate metrics for the problem type, balancing accuracy, interpretability, calibration, and operational feasibility.
• Produce model documentation covering methodology, assumptions, validation approach, performance benchmarks, and known failure modes.
• Monitor deployed models for drift and degradation, and participate in retraining and re-validation cycles as needed.
• Collaborate with AI Engineering when models are ready for production deployment, providing methodology documentation and supporting the handoff process.

Data Exploration and Problem Framing:

• Partner with business function to translate business questions into well-scoped analytical problems with clear success criteria and measurable outputs.
• Conduct exploratory data analysis (EDA) to understand data distributions, quality issues, and structural patterns before committing to an analytical approach.
• Advise on measurement strategy, testability, and data requirements upstream, flagging when a question cannot be answered reliably with available data.
• Identify the appropriate analytical method for each problem, knowing when simple statistical tests are sufficient versus when more complex modeling is warranted.
• Surface data quality issues discovered during analysis and escalate them to Data Engineering with clear documentation of the impact.

Analytical Quality and Reproducibility:

• Write clean, well-documented, and reproducible code; all analytical work should be re-runnable and reviewable by a peer without additional explanation.
• Participate actively in code review, both submitting work for review and reviewing peers' analytical code for methodological soundness and code quality.
• Apply appropriate corrections for multiple comparisons, report effect sizes alongside p-values, and communicate uncertainty honestly in all deliverables.
• Contribute to shared analytical frameworks, reusable templates, and reference implementations that raise the methodological standard across the team.
• Ensure all deliverables meet the COE's data product certification standards before release.

Partnership with Cross-Functional Teams:

• Work closely with the business functions as the quantitative execution partner, receiving analytically defined questions and returning rigorous, well-documented findings.
• Communicate statistical methodology, uncertainty, and analytical limitations clearly and, where needed, to non-technical audiences.
• Partner with Analytics Engineering to connect statistical output to the governed reporting layer, ensuring model scores, segments, and analytical results are operationalized correctly.
• Participate in sprint ceremonies, peer reviews, and COE-wide delivery forums as an active contributor.
• Frame high-value problems directly with senior business leaders, set the scientific standards for the data science practice, and mentor data scientists operating self-sufficiently.

Requirements:

• PhD or Master's degree in a quantitative field (statistics, mathematics, econometrics, computer science, or a related discipline) required.
• 8+ years of experience in data science, statistical analysis, or applied quantitative research in a professional environment.
• Strong proficiency in Python for statistical and data science workloads: pandas, numpy, scipy, statsmodels, scikit-learn.
• Deep working knowledge of statistical methodology: hypothesis testing, regression analysis, experimental design, causal inference, and Bayesian methods.
• Demonstrated experience applying advanced quantitative methods survival analysis, time-series analysis, clustering, or simulation to real business problems.
• Hands-on experience with Databricks for data exploration, collaborative analysis, and notebook-based workflows.
• Ability to communicate statistical findings clearly and honestly to both technical peers and non-technical stakeholders.
• Experience working in a structured delivery environment with sprint cadences and cross-functional collaboration.
• Experience in a regulated industry (life sciences, healthcare, financial services) where analytical methodology is subject to scrutiny or audit.
• Consulting experience in data science and insights delivery roles.
• Familiarity with quasi-experimental and non-experimental causal inference methods.
• Experience contributing to model handoffs with an AI/ML engineering team, including documentation and validation support.
• Experience working in a global capability center (GCC) or center of excellence (COE) environment.