Staff Applied Scientist, LTV Modeling
About this role
Developing the core long-term value measurement framework involves defining discovery impressions, prioritizing hypotheses, and laying out an experimentation roadmap to validate how retail partnerships grow. Day-to-day responsibilities center on building v0 of the lifetime value model, running long-running ranking experiments, and delivering a surrogate metric that predicts long-term marketplace dynamics while managing confounding factors.
The Discovery team operates at the intersection of machine learning and economic modeling to help retailers discover brands that build lasting, successful partnerships. Candidates who thrive here possess deep causal inference expertise and enjoy solving complex optimization problems without a pre-existing playbook.
What you will do
- Own how the platform measures and optimizes the long-term value of a discovery impression to strengthen relationships between independent retailers and brands.
- Create the initial lifetime value framework by forming and prioritizing hypotheses about long-term relationship value and trade-offs.
- Lead the implementation of the initial model version into a long-running ranking experiment with defined north star metrics and guardrails.
- Deliver a long-term surrogate metric that provides near-term readouts predictive of long-term value while accounting for confounding factors.
- Manage the lifetime value model tech stack and operating standards while continuously improving accuracy for search, reorder, and ads teams.
What you need
- Bring 5 or more years of experience applying machine learning and statistical modeling to real business problems and shipping them to production.
- Demonstrate deep causal inference expertise including quasi-experimental methods, rigorous confounder control, and critical analytical evaluation.
- Possess strong experimentation design skills focused on long-horizon experiments, surrogate proxy metrics, and variance reduction.
- Have baseline knowledge of search and recommendation systems operating on e-commerce or marketplace platforms.
- Exhibit strong statistical analysis and data engineering skills covering SQL, ETL, and large-scale data transformation.
Nice to have
- PhD in Computer Science, Statistics, Economics, Operations Research, or a related STEM field
- Experience with lifetime value optimization on two-sided marketplaces, e-commerce platforms, or recommendation systems
- Familiarity with deep learning, machine learning, or learning-to-rank techniques
Benefits
- Competitive pay
- Equity
- Comprehensive benefits
- Hybrid remote flexibility up to 4 weeks per year
Skills and tech stack
Questions candidates ask
What is the remote work policy for this role?
Faire employees currently go into the office 3 days per week on Tuesdays, Thursdays, and a third flex day of their choosing. Additionally, hybrid in-office roles have the flexibility to work remotely up to 4 weeks per year.
What is the salary range for the position?
The pay range for this role in San Francisco and New York is $246,500 to $339,000 per year, and the position is also eligible for equity and benefits.
What team does this position sit on?
This position sits on the Discovery team, owning how the platform measures and optimizes the long-term value of a discovery impression.