ML Engineer: Personalization & Recommender (Hybrid, Equity)

Pinterest Engineering; San Francisco (CA); Hybrid; USD 163,000 - 286,000; Full time

Job summary

Pinterest is seeking an experienced ML Engineer for Ads ML Engineering to develop and execute the evolution of the ML stack powering advertising on Pinterest. You’ll drive end-to-end ML projects, from data pipelines to model deployments, with a strong emphasis on personalization and scale.

You will collaborate with multiple teams to push the boundaries of recommender systems, use LLMs to improve content understanding, and work in a hybrid work environment based in San Francisco or US-based

Qualifications

• 2+ years of industry experience applying machine learning methods.
• Bachelor’s degree in computer science, machine learning, statistics, or related field.
• End-to-end hands-on experience with building data processing pipelines and large-scale ML systems.
• Practical knowledge of large scale recommender systems or modern ads ranking/ retrieval.
• Nice to have: publications at top ML conferences, AI coding assistants (Cursor, Copilot, Codex), LLM-powered productivity tools, scalable realtime systems, passion for applied ML and Pinterest product, background in computational advertising.

Responsibilities

• Build cutting edge ML systems to personalize Pinterest.
• Collaborate with cross-functional teams to improve ML models for Homefeed, Ads, Growth, Shopping, and Search.
• Leverage data to improve candidate retrieval.
• Work in a high-impact environment with quick experimentation and launches.
• Keep up with industry trends in recommendation systems.
• Leverage LLMs to enhance content understanding.

Skills

ML experience

Recommender systems

Data pipelines

Big data

Publications

Education

Bachelor's degree in CS/ML/Statistics

Tools

Hadoop/Spark

Job description

Pinterest is seeking an experienced ML Engineer for Ads ML Engineering to develop and execute the evolution of the ML stack powering advertising on Pinterest. You’ll drive end-to-end ML projects, from data pipelines to model deployments, with a strong emphasis on personalization and scale.

You will collaborate with multiple teams to push the boundaries of recommender systems, use LLMs to improve content understanding, and work in a hybrid work environment based in San Francisco or US-based