Skip to main content

NewsBreak

Matching Algorithm Engineer

Mountain View, California, United StatesFrom $400kmidAdded 1 month ago

About this role

As a Matching Algorithm Engineer at NewsBreak, you'll develop models that enhance connections between local consumers and businesses in a dynamic marketplace. Your work will focus on improving search ranking, matching, and dispatch systems to optimize conversion rates using modern machine learning techniques.

What you'll do

  • Develop search-ranking and dispatch models for a local marketplace.
  • Manage end-to-end learning-to-rank and retrieval pipelines.
  • Enhance marketplace conversion through advanced matching models.
  • Conduct experiments to measure causal impact in marketplace settings.
  • Incorporate advanced ML/LLM techniques into existing systems.

What they're looking for

  • 4+ years in ML Engineering or Applied Science
  • Experience with two-sided marketplace matching
  • Strong experimentation and causal methods
  • Production ML at scale
  • Expertise in ranking and retrieval pipelines

Benefits

  • Competitive base salary range of $163,000 - $400,000
  • Potential for discretionary bonuses and stock options
  • [other benefits may be provided]
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

NewsBreak

NewsBreak operates a news and local marketplace platform serving 40M+ monthly active users, leveraging machine learning and data infrastructure to power recommendations, advertising, and matching between consumers and businesses. The company is hiring software engineers, ML engineers, and data specialists to build and optimize backend systems, ML infrastructure, recommendation engines, and algorithms that drive user engagement and monetization.

View all jobs at NewsBreak

Likely interview questions

  • Walk us through a ranking or matching model you built that directly improved marketplace conversion. How did you measure the impact?
  • Describe your experience with learning-to-rank pipelines. What retrieval and ranking techniques have you used, and how did you optimize for both relevance and latency?