Senior Data Scientist

• Lead Data Science in Designing Prototypes Supporting Commercial Strategy
• Own applied data science problem framing: translate business goals into clear hypotheses, success metrics, and an analytical approach (e.g., forecasting, propensity, segmentation, optimization, NLP)
• Lead the design and delivery of data science prototypes aligned to commercial strategy, ensuring measurable business impact (e.g., cost savings, revenue growth, improved guest experience)
• Define and execute measurement and experimentation plans (e.g., A/B tests, holdouts, quasi-experiments) to quantify incremental impact and guide product/business decisions
• Plan and manage the data science / ML project pipeline by developing roadmaps, aligning business priorities, communicating tradeoffs, and coordinating dependencies with partners (e.g., Data Engineering, Data Governance, Product/Digital/Business teams)
• Identify, collect, and validate datasets
• define data quality checks and partner with data stewards/engineering to ensure data is fit for purpose
• Design, develop, and evaluate models and prototypes
• select the best approach balancing accuracy, interpretability, scalability, and business constraints
• Present insights and recommendations to non-technical and leadership audiences, driving alignment, decision-making, and adoption
• Raise the bar on team quality: conduct peer code reviews, mentor team members, and document approaches (Confluence) to establish reusable patterns and best practices
• As applicable, manage third parties during the prototyping phase to ensure schedules, processes, and outcomes are monitored and achieved
• Support Machine Learning Deployments
• Develop, test, optimize, and productionize machine learning models, including their supporting data pipelines for training and predictions
• Develop and embed automated processes for predictive model validation and QA
• Stage deployments to enable collaborative QA and controlled releases, monitor and version control changes
• Monitor health and performance of production ML products and relative performance of competing models
• Promote, contribute, and define coding guidelines to raise the bar for code quality
• Develop and Support Generative AI Solutions
• Develop and optimize Gen AI workflows using LLMs, RAG, vector search, and AI orchestration frameworks
• Partner with engineering, integrations, and platform teams to support deployment of LLM-based applications, including retrieval pipelines, and prompt orchestration and governance across development and production environments
• Design evaluation suites and QA approaches for GenAI solutions (e.g., test sets, automated checks, human review), including responsible AI guardrails appropriate to the use case
• Contribute to reusable AI components, prompt engineering standards, and AI solution design best practices
• Partnerships and Following Four Seasons Standards
• Follows technical direction set by Enterprise Data Architect and Data Engineering team
• Manage data science projects from conception to delivery through the organized intake process, track tasks and progress using Jira and Monday.com, and adhere to governance standards and successful delivery methodologies
• Learn and implement Four Seasons technical standards, procedures and processes including FS DevOps
• Test and verify the completion of work done by Data Engineering to ensure compliance with the original intent of prototype and long-term requirements

• 5+ years of working experience in data science, data wrangling, management, and/or ML engineering
• University degree in Computer Science, Statistics, Data Science, Applied Mathematics, Engineering, or substantial coursework in relevant quantitative field
• Applied modeling and analytics: strong foundation in statistics and ML (supervised/unsupervised), feature engineering, and model evaluation
• ability to explain tradeoffs and drive business decisions
• Experience in NLP and/or GenAI techniques for applied use cases (e.g., classification, entity extraction, semantic search) with an evaluation-first mindset
• Data proficiency: advanced SQL and Python
• strong data wrangling skills (profiling, cleansing, merging, validation) for large, messy datasets
• Cloud & tooling (preferred): Azure and Databricks ecosystem (e.g., Databricks, Data Factory, Data Lake/Blob, Azure Function App, Azure AI Foundry), with ability to run scalable experimentation and modeling workflows
• Production readiness (in partnership with Engineering): familiarity with CI/CD, version control (Azure DevOps/GitHub), reproducible pipelines, and monitoring principles for models and data products
• Visualization & communication: experience using notebooks and BI tools (e.g., Power BI, Tableau, PowerPoint) to tell clear stories to technical and non-technical stakeholders
• Experimentation and measurement: experience designing and interpreting experiments (A/B tests, holdouts, quasi-experiments) and defining success metrics for product/business outcomes
• Proactive to understand business needs and how data will be used to drive strategic decisions and tactical action plans
• Translates data science outputs to provide clear, actionable recommendations that support leadership decision-making
• Tailors messaging to the audience, focusing on clarity, brevity, and relevance
• Collaborate effectively with cross-functional colleagues, external consultants, and agencies
• Works well under pressure and can manage multiple tasks under time constraints
• Well organized, detail-oriented, able to multi-task in a highly iterative environment
• Creative, performance-driven problem solver with a strong sense of ownership and discipline
• passionate about leveraging digital, AI, ML, and data to drive business transformation
• Solid foundation in Math and Statistics
• Ability to sift through large data sets, identify patterns and know how to use that data to come to meaningful and actionable conclusions
• Work cross-functionally in a matrix organization
• Project Management: Organize and manage processes and expectations, and deliver according to key deadlines

Cloud & tooling: Azure and Databricks ecosystem (e.g., Databricks, Data Factory, Data Lake/Blob, Azure Function App, Azure AI Foundry), with ability to run scalable experimentation and modeling workflows