SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 246,500 - 339,000 / annual
Faire is a technology wholesale platform connecting independent retailers globally with products and brands. The company uses machine learning and data to power a multi-hundred-billion-dollar wholesale marketplace.
As a Staff Applied Scientist on the Discovery team, you will own how Faire measures and optimizes the long-term value (LTV) of discovery impressions—one of the highest-leverage problems on the marketplace. Today's ranking algorithms optimize for order conversion, but the opportunity is deeper: helping retailers find brands they can build lasting, successful partnerships with. Reordering signals these successful relationships, which compound into substantial volume over time.
You will define this measurement problem from first principles, building the LTV framework, designing experiments to validate it, and turning results into a shared signal that all discovery algorithms can act on.
Key responsibilities:
- Own measurement and optimization of long-term value of discovery impressions, including how they contribute to discovering new brands and strengthening promising relationships.
- Create the initial LTV framework by forming and prioritizing hypotheses about what drives long-term relationship value, making assumptions explicit and testable, and laying out the experimentation roadmap.
- Lead implementation of v0 LTV model into long-running ranking experiments, setting north star metrics and guardrails to maximize organizational learning with defined readout cadence and course-correction plans.
- Deliver long-term surrogate metrics—near-term readouts predictive of long-term value—accounting for confounding factors and measurement uncertainties.
- Own the LTV model tech stack and operating standards, continuously improving model capabilities and accuracy as it scales across search, reorder, and ads.
The role is hybrid with 3 days per week in office (Tuesdays, Thursdays, and one flex day), with flexibility to work remotely up to 4 weeks annually.
REQUIREMENTS:
- 5+ years applying ML and statistical modeling to real business problems, shipping to production
- Deep causal inference expertise: quasi-experimental methods, rigorous confounder control, and healthy skepticism of analytical results
- Strong experimentation design skills, especially for long-horizon experiments with surrogate/proxy metrics and variance reduction for sparse, delayed outcomes
- Baseline knowledge of search and recommendation systems on e-commerce or marketplace platforms
- Strong statistical analysis and data engineering skills: SQL/ETL and data transformation at scale
- Excitement and willingness to learn new tools and techniques
- Excellent communication skills and ability to work in highly cross-functional teams
BONUS:
- PhD in CS, Stats, Economics, OR, or related STEM field
- LTV/lifetime-value optimization experience on two-sided marketplaces, e-commerce platforms, or recommendation systems
- Deep learning, machine learning, or learning-to-rank techniques
