Sr. Data Scientist

Reports to: Director of Data & Analytics

Collaborates closely with: Senior Product Manager, Marketplace (dotted line)

We're looking for a Senior Data Scientist to help build the analytical and algorithmic foundation of our marketplace as we scale the business. You'll work at the intersection of data, product, and engineering — establishing the metrics and models that keep supply and demand in balance, while building toward pricing algorithms and retention strategies that support long-term marketplace health.

This is a hands-on, high-visibility role. In the near term, you'll focus on getting the data foundation right — clean definitions, reliable dashboards, and rigorous measurement — while also starting to build the pricing and engagement models that will define the marketplace's next phase. You'll partner with the Director of Data & Analytics and the Senior Product Manager for Marketplace to turn analysis into action.

Marketplace Measurement & Health

• Own and continuously refine core marketplace definitions (e.g., active supply/demand, fill rate, instant-bid counting) to ensure metrics are accurate and consistent across teams.

• Lead experimentation strategy and rigor across product, growth, and monetization bets that often run at once, from test design and power analysis through to clean readouts leaders can trust.

• Apply causal-inference methods (difference-in-differences, synthetic control, propensity, Bayesian) to the many high-stakes questions we can't cleanly A/B, such as market- or country-level pricing and fee changes and supply-side availability shifts, and be honest about power and incrementality when reads are thin.

• Improving experimentation frameworks, metrics strategy, and analytical rigor across teams — developing scalable approaches for measurement, segmentation, forecasting, and incrementality

• Guide the data team in building and maintaining the dashboards that give real-time visibility into marketplace health. This is an ongoing, hands-on responsibility, not a one-time setup.

• Monitor supply/demand balance across markets and segments, flagging imbalances and proposing data-driven fixes.

Algorithms & Growth Models

• Analyze pricing, supply, and demand data to develop models and recommendations that inform dynamic pricing strategy.

• Partner with engineering to help operationalize data models, iterating based on real-world results.

• Identify markets, segments, or categories where targeted growth efforts (incentives, supply expansion, etc.) would have the most impact.

• Analyze dispatch performance (offer volume, sequencing, and pacing) to improve match rates and the cleaner experience, and partner with engineering to build and iterate on the recommendation and ranking models that power how jobs are matched to cleaners.

• Develop and refine the scoring and quality models that shape cleaner job access, including identifying the behaviors that drive strong outcomes and validating that the score reflects real marketplace health.

Retention & Engagement Analysis

• Analyze user behavior patterns to identify the drivers of disintermediation (users leaving the platform after an initial connection) and quantify its impact on marketplace revenue and health.

• Build the analytical case for disintermediation-prevention efforts — surfacing which user segments, markets, or behaviors are highest-risk — to guide product and customer success in designing prevention strategies.

• Partner with product and customer success to test and measure the effectiveness of engagement and loyalty initiatives aimed at increasing repeat transactions and trust in the platform.

• Build models and analyses that inform (not unilaterally set) broader retention and loyalty strategy.

Cross-functional Collaboration

• Partner directly with directors, the Marketplace PM, engineering, and CS/ops to frame complex, cross-functional problems and translate analysis into clear recommendations that drive action.

• Support ad hoc, deep-dive analyses as new questions or opportunities come up during the pilot.

• 5+ years in data science, ideally with marketplace, pricing, or growth exposure. Bachelor's in a quantitative field (CS, Statistics, Applied Math, Economics, ML, Physics, or similar); advanced degree a plus.

• Advanced SQL proficiency and strong Python fluency, with the ability to work across large, complex datasets

• Strong foundation in experimentation and causal inference: A/B testing plus methods for when clean tests aren't possible 

• Hands-on experience building predictive or ML models and taking them from analysis toward production in partnership with engineering. Recommendation, ranking, or scoring model experience is a strong plus.

• Experience deploying or operationalizing models using platforms such as AWS SageMaker, Google Cloud AI (Vertex AI), or similar ML platforms is a strong plus.

• Depth in one or more of pricing and monetization, growth and retention, segmentation and lifecycle, or marketplace and operational analytics, ideally in a two-sided marketplace.

• Comfort operating with ambiguity — pilot-stage data isn't always clean, and you'll help make it so.

• Excellent communication skills; able to translate complex analysis into clear recommendations for non-technical stakeholders.

• A collaborative mindset — this role sits at the center of data, product, and engineering.