Senior Data Scientist

Position Summary:

Swiftly is searching for a Senior Data Scientist to join our Data Science and Analytics team to build and ship machine learning models that power retail media and marketing measurements. This role will own data science projects end to end, from sourcing and shaping data in our Databricks lakehouse to developing models and delivering monitored, production-ready pipelines, with a strong understanding of the upstream data infrastructure and datasets that support machine learning. A key focus is marketing analytics: working closely with analytics and data engineering teams to measure and improve campaign performance across channels using approaches such as ROAS, incrementality testing, and marketing mix modeling. The ideal candidate is a curious problem solver who prioritizes data quality, observability, testing, and monitoring, collaborates well across teams, and is comfortable leveraging AI tools like Claude in their day-to-day work.

This is a full-time contract role. We use Deel as the employer of record and contract.

Responsibilities Include:

• Build, validate, and A/B test predictive models that drive marketing and shopper outcomes
• Develop and improve campaign measurement approaches, including ROAS/iROAS, incrementality and holdout testing, and marketing mix modeling, and translate results into clear recommendations for business stakeholders
• Own data science projects end to end: data sourcing, feature engineering, model development, business-friendly output, and a production machine learning pipeline
• Source and process large-scale, multi-tenant retail data using Python, Spark, and SQL in Databricks, including writing SQL and creating views and tables
• Build and maintain upstream pipelines and well-modeled datasets that support downstream models, partnering with analytics and data engineering teams to define data contracts, quality expectations, and shared metric definitions
• Implement testing, data observability, and monitoring across machine learning and data pipelines, including data quality, model performance, and drift checks
• Create dashboards and alerts for model, pipeline, and data monitoring
• Partner with Data Analysts and Data Engineers to answer data questions, offload repeatable processes, and help ensure reports are accurate
• Proactively identify failure points, own the whole process, and solve complex data and pipeline issues
• Leverage AI tools (such as Claude) in day-to-day work to improve productivity and quality
• Participate in a rotating on-call schedule
• Other related duties as assigned

Required Qualifications:

• 5+ years of professional experience across data science, applied machine learning, and data engineering, with strong Python, SQL, and Spark skills, including hands-on experience working in Databricks
• Hands-on experience developing marketing or advertising models, such as campaign measurement (ROAS, incrementality), marketing mix modeling, attribution, or audience/propensity and uplift modeling
• Experience building, deploying, and monitoring predictive and machine learning models in production
• Strong foundation in statistics and experimental design (e.g., hypothesis testing, regression, causal inference)
• Strong understanding of data modeling, data pipelines, and ETL processes, with hands-on experience building the views, tables, and transformations that support machine learning models and analytics
• B.S. in Mathematics, Statistics, Computer Science, Computer Engineering, or a related field
• Operational experience working with large-scale data warehouses and/or data lakes
• Proven ability to collaborate with data analysts, data engineers, and internal stakeholders, and to work in an ambiguous, fast-paced environment
• Ability to leverage AI tools in day-to-day work
• Build data products that are well-modeled, documented, and easy to understand and maintain

Preferred Qualifications:

• Experience in marketing, retail, CPG, e-commerce, or retail media/ad tech
• Experience designing and analyzing A/B tests, holdout and geo experiments, and incrementality studies
• Experience with Databricks platform capabilities
• Experience with LLM, embedding, or NLP-based approaches (e.g., product classification or matching), including using tools such as Claude
• Experience with data visualization, observability and monitoring dashboards (e.g., Grafana or Databricks SQL dashboards or Tableau)
• Experience with ad-hoc analysis and data visualization