Machine Learning Engineer, Applied Research

Whatnot is seeking a Machine Learning Engineer for Applied Research to lead end-to-end applied research and modeling efforts that improve how marketplace experiments and decisions are evaluated. This NYC-based role works in a hybrid format and focuses on marketplace dynamics across simulation, auction mechanics, long-term outcomes, and robust experimentation.

Responsibilities

• Lead research projects within the marketplace dynamics area, including simulation, auction and allocation mechanics, long-term objective modeling, exploration and information value, and marketplace experimentation methods.
• Drive ideas from hypothesis to production through activities such as literature review, prototyping, offline validation, shadow testing, and online experiments delivered via partner teams across Discovery and the Seller org.
• Build system-level models of marketplace behavior, including learned simulators that estimate segment-level effects of ranking and policy changes, plus surrogate models for long-term marketplace outcomes.
• Model Whatnot’s market mechanics, covering auction and bidding dynamics and discovery exposure allocation as a portfolio problem, including allocation to rising sellers.
• Improve evaluation of changes in a multi-sided live marketplace using techniques such as off-policy evaluation, switchback and interference-robust experiment designs, and variance reduction.
• Strengthen Whatnot’s external technical presence through publications, open-source contributions, and public benchmarks.

Requirements

• 5+ years of industry experience building and deploying machine learning models to solve user problems at scale.
• Deep expertise in at least one area, such as recommendation systems, causal inference, off-policy evaluation, reinforcement learning and bandits, auction or mechanism design, or marketplace experimentation.
• Proven ability to apply scientific methods to real-world problems using consumer-scale data.
• Advanced proficiency in Python and SQL, along with common ML frameworks such as PyTorch and XGBoost.
• Strong foundation in applied statistics, experiment design, and theoretical machine learning.
• Strong communication and leadership skills, including the ability to influence roadmaps and align cross-functional teams in a remote environment.

Preferred Qualifications

• Experience in two-sided marketplaces, ads and auction systems, or pricing.
• Experience building simulators or economic models of platform behavior.

Technologies

• Python
• SQL
• PyTorch
• XGBoost

Compensation

• USD 207,000 - 290,000 per year
• For full-time, US-based applicants: $207,000/year to $290,000/year plus benefits and equity.

Benefits

• Flexible Time Off Policy and company-wide holidays, including a spring and winter break.
• Health Insurance options: Medical, Dental, Vision.
• Work From Home support.
• Home office setup allowance.
• Monthly allowance for cell phone and internet.
• Monthly allowance for wellness.
• Annual allowance towards childcare.
• Lifetime benefit for family planning, including adoption or fertility expenses.
• Retirement support: 401k offering for Traditional and Roth accounts in the US with employer match up to 4% of base salary, and pension plans internationally.
• Monthly allowance to dogfood the app.
• Parental leave, including 16 weeks of paid parental leave plus one month of gradual return to work.

Location and Work Arrangement

New York, NY (Hybrid). Team members in this role must be within commuting distance (50 miles) of the New York City hub.

Additional Information

• Whatnot will only contact candidates through official @whatnot.com email addresses. If you see an email impersonating a Whatnot recruiter, disregard it and report it as spam.
• EOE: Whatnot is an Equal Opportunity Employer.