4 hours ago
Base Salary
$150k - $300k/yr
Responsibilities
- Build and own production recommendation and ranking systems for feed surfaces, including candidate generation, online experimentation, and monitoring.
- Design an event-triggered engagement engine covering condition detection, propensity and uplift modeling, frequency management, and holdouts.
- Build customer-to-professional matching systems that evolve from transparent rules to learned ranking under explicit fairness and exposure constraints.
- Define evaluation frameworks incorporating downstream outcomes, complaints, and “do not proceed” recommendations as objectives.
- Contribute insights to pricing and intent models owned by the AI team.
Requirements
- Require 5+ years of machine-learning or software engineering experience, including 3+ years shipping recommendation or ranking systems in production.
- Require experience building and operating ranking systems at consumer scale for millions of users, including candidate generation, ranking, and monitoring.
- Require substantial online experimentation experience and the ability to explain a failed ranking test and its causes.
- Require production deployment of an uplift, causal, or counterfactual model, or a rigorous explanation of why click-based objectives are inappropriate for rare, high-cost decisions.
- Require strong Python and at least one of Java, Scala, or Go, plus production experience with feature stores and streaming pipelines.
- Require the ability to explain modeling decisions to product and business stakeholders and defend experimental design under commercial pressure.
- Prefer experience with feed or notification ranking, two-sided marketplace matching with fairness or exposure constraints, high-consequence domains, or publications and open-source contributions in recommendation, causal inference, or marketplace design.
Benefits
- This is a full-time position with eligibility for a discretionary bonus and options depending on the position.
- The employer states that the overall rewards package is designed to attract top talent.
Categories
About NewsBreak
NewsBreak builds a local-news aggregation and discovery platform for U.S. consumers on web and mobile, powered by recommendation systems and NLP. It partners with publishers and independent creators and monetizes primarily through advertising for local and national businesses. Founded in 2015 and headquartered in Mountain View, California, the platform serves over 40 million monthly active users and aggregates content from more than 10,000 sources.