Senior Data Scientist, Experimentation (Marketing)

Senior Data Scientist, Experimentation (Marketing)

Note: This position is not eligible for Immigration Sponsorship at this time.

Fractal is a strategic AI partner to Fortune 500 companies with a vision to power every human decision in the enterprise. Fractal is building a world where individual choices, freedom, and diversity are the greatest assets. An ecosystem where human imagination is at the heart of every decision. Where no possibility is written off, only challenged to get better. We believe that a true Fractalite is the one who empowers imagination with intelligence. Fractal has been featured as a Great Place to Work by The Economic Times in partnership with the Great Place to Work® Institute and recognized as a ‘Cool Vendor’ and a ‘Vendor to Watch’ by Gartner.

Please visit Fractal | Intelligence for Imagination for more information about Fractal.

Summary:

We're looking for a top-notch Senior Data Scientist to lead the design, execution, and statistical methodology of our experimentation program. You will join our cross-functional Optimization team comprised of Data Scientists, Creatives, Developers, and Producers. You will own end-to-end test analysis, drive the statistical methodology underpinning Stats Engine, and serve as the technical authority on experimentation best practices across the client’s marketing organization which includes Channel Digital, email marketing, social media, and paid media.

If you're passionate about the intersection of marketing, data science, and experimentation — and are energized by the opportunity to shape how a world-class brand makes data-driven decisions at scale — we encourage you to apply.

KEY QUALIFICATIONS

• Deep expertise in experimentation design and statistical hypothesis testing — including sample size determination, power analysis, confidence intervals, p-values, and multiple testing corrections.
• Strong command of advanced statistical methods including sequential testing (SPRT, alpha-spending functions), variance reduction techniques (CUPED), and Bayesian inference.
• Experience with dynamic optimization methods such as Multi-Armed Bandits (Thompson Sampling, Upper Confidence Bound) and their application in marketing or digital product contexts.
• Proficiency in causal inference methods including synthetic control, Difference-in-Differences, and quasi-experimental design — particularly for geo-targeted or always-on marketing contexts where traditional A/B testing is not feasible.
• Strong data querying skills (SQL) and fluency in a scripting language (Python or R) for statistical analysis, data wrangling, and results automation.
• Excellent communication and presentation skills with the ability to translate complex statistical findings into clear, actionable insights for diverse audiences including creatives, producers, and marketing leaders.
• Proven ability to manage multiple experimentation projects across different stages of development simultaneously, with strong attention to detail and quality standards.
• Team player who thrives in a cross-functional environment and takes pride in elevating the statistical rigor of the teams around them.

Highly beneficial (but not required)

• Experience with multi-geo test execution and localization considerations across global markets.
• Familiarity with experimentation platforms such as Adobe Target or Optimizely, and experience partnering with platform engineering teams on analytics implementation.
• Experience applying ML algorithms — regression, decision trees, clustering — to marketing measurement or audience segmentation problems.
• Background in marketing analytics, digital attribution, or media measurement.

DESCRIPTION

Core responsibilities cover three pillars:

EXPERIMENT DESIGN & ANALYSIS:

Own the end-to-end statistical design and analysis of A/B tests across, email (DM), and Channel Digital platforms. Develop test proposals that define populations, KPIs, runtime requirements, and minimum detectable effects. Analyze results with rigor, develop clear insights, and deliver recommendations that drive confident decision-making.

Apply advanced statistical methods — including sequential testing, CUPED variance reduction, and Bayesian approaches — to increase the speed and sensitivity of the experimentation program. Apply causal inference methods for always-on optimization scenarios and geo-targeted campaigns where traditional A/B testing is not feasible.

STATS ENGINE METHODOLOGY & PLATFORM:

Serve as the statistical methodology owner for Stats Engine — Client's proprietary experimentation platform. Define, validate, and document the statistical methods embedded in the platform, ensuring all automated calculations meet the highest standards of accuracy and rigor.

Partner with the Product Manager and Client's AiDP engineering team to translate methodological requirements into platform specifications. Contribute to the evolution of Stats Engine through Phases 2–4, including sequential testing sup