Senior Applied AI/ML Scientist - Marketplace Quality

Faire•San Francisco, CA

4d•$211,000 - $290,500•Hybrid

About The Position

Faire leverages the power of machine learning and data insights to revolutionize the wholesale industry, enabling local retailers to compete against giants like Amazon and big box stores. Our highly skilled team of Applied AI/ML Scientists specialize in developing algorithmic solutions for notification and recommender systems, advertising attribution, and LTV predictions. We are dedicated to building machine learning models that help our customers thrive. As a Senior Applied AI/ML Scientist on the Marketplace Quality team, you will own the modeling and measurement that keeps Faire's marketplace trustworthy for the hundreds of thousands of independent brands and retailers on it. Retailers need confidence that the price and the product they see on Faire are the real thing. That means matching Faire's catalog against messy external data at scale, detecting pricing and policy violations with calibrated confidence, and deciding which violations are worth acting on given a finite operations budget. You will work across structured and unstructured data (listing text, product images, external web listings, transaction history) using entity resolution, information extraction, multi-modal LLMs, calibrated classification, constrained optimization, and experimentation. You will drive projects end-to-end from framing through production and measurement, partnering closely with product, engineering, and our marketplace operations team. Our team already includes experienced Applied AI/ML Scientists from Uber, Airbnb, Square, Facebook, and Pinterest. Faire will soon be known as a top destination for data scientists and machine learning engineers, and you will help take us there!

Requirements

3+ years of industry experience using machine learning to solve real-world problems.
Experience with relevant business problems (e-commerce, marketplaces, catalog and content quality, search, or personalization).
Experience with relevant technical methods (deep learning and LLMs, computer vision, information extraction, entity resolution, ranking, and/or experimentation and causal inference).
Strong programming skills.
An excitement and willingness to learn new tools and techniques.
The ability to drive a project end-to-end and lead model development with limited supervision.
Strong communication skills and the ability to work in a highly cross-functional team.

Nice To Haves

Highly recommended: Master's or PhD in Computer Science, Statistics, or related STEM fields.
Previous experience with catalog quality, product attribute extraction, computer vision for e-commerce imagery, or search and discovery for a two-sided platform.
Experience building and validating LLM evaluation pipelines, including prompt iteration against labeled data and human-in-the-loop workflows.

Responsibilities

Own applied ML projects end-to-end: framing the problem, building and shipping the model, and measuring impact on the marketplace.
Build and improve pricing-integrity models that compare Faire listings against external pricing signals and detect over- and under-pricing violations with a calibrated confidence bar.
Solve product matching and entity resolution at scale: link Faire's catalog to external listings using text and image embeddings, retrieval, and multi-modal LLMs, and build the match-quality and gating models that make downstream detection trustworthy.
Extract structured attributes from unstructured listing content (descriptions, images, third-party sources) to power detection and enrichment.
Turn model scores into action: design the targeting and prioritization logic that ranks violations by expected marketplace impact against the cost of a false positive, under a constrained human-review budget.
Build human-in-the-loop systems with our marketplace operations partners: design audits, generate training labels, set precision bars, and close the loop from review outcomes back into the models.
Design and analyze experiments for enforcement levers such as downranking, badging, and brand-facing remediation, and measure their effect on retailer trust and marketplace GMV.
Partner across product, engineering, operations, and analytics to turn models into shipped product and business impact.
Solve challenging problems related to a two-sided marketplace.