FlexWork
P

Staff Machine Learning Engineer, Homefeed & Search Quality

Pinterest
Full-Time Remote Canada
$90,000 – $160,000 / year
PythonJavaMachine LearningTensorFlowPyTorch

Job description

Pinterest helps Pinners discover and do what they love. Most of that discovery happens on three surfaces: Homefeed, Search and Related Pins. The Home & Search Quality team decides what hundreds of millions of people see every month on those surfaces. We build the retrieval, ranking and blending systems that make each one personal, relevant and worth coming back to.

We're looking for a Tech Lead for ranking and blending who can drive engineering work across teams and turn state-of-the-art machine learning into better experiences for Pinners. You'll work on large-scale, low-latency systems and models that directly move Pinner engagement and business metrics.

 

What will you do:

  • Set the technical direction for ranking and blending on Homefeed, Search and Related Pins, and move the three surfaces toward shared models and shared wins.
  • Build and adapt large foundation models (transformer-based user and content models) into ranking models for each surface.
  • Optimize for long-term value: rank and blend for what brings Pinners back, not only for the next click, while keeping results relevant and high quality.
  • Develop signals for relevance, quality and intent (for example, LLM- and VLM-based embeddings) that are reused across the stack.
  • Make the final ranking stage learned and adaptive, replacing hand-tuned rules and weights.
  • Partner with retrieval, foundation-model, infrastructure and product teams so improvements land across the full stack, from candidate generation to the final page.
  • Mentor and tech-lead a team of 7-10 engineers.

 

What we are looking for:

  • Languages: Python, Java
  • Machine learning: PyTorch, TensorFlow
  • Big data processing: Spark, Hive
  • Experience building ranking or recommendation systems at scale, for feeds, search or both
  • Strong modeling skills, including multi-objective optimization, sequence-based user modeling, online/offline bias and model scaling
  • Hands-on experience using LLMs and VLMs to drive product impact
  • Experience with large-scale, low-latency production systems and online experimentation

What skills are preferred but not required?

  • Search relevance experience, especially semantic relevance modeling
  • Experience with reinforcement learning, whole-page optimization or long-term (retention) objectives
  • Experience with generative AI models
  • Experience making ML models more efficient to train and serve
  • Experience working closely with product managers and designers to ship ML-driven, user-facing products
  • Bachelor’s degree in Computer Science, Engineering, or a related technical field—or equivalent practical experience.
  • Minimum 7 years of industry experience in ML engineering / applied ML / software engineering, including meaningful time operating as a Staff-level (or equivalent) IC delivering complex production systems

Relocation Statement:

  • This position is not eligible for relocation assistance. Visit our PinFlex page to learn more about our working model.

In-Office Requirement Statement:

  • We recognize that the ideal environment for work is situational and may differ across departments. What this looks like day-to-day can vary based on the needs of each organization or role.
  • This role will need to be in the office for in-person collaboration 1-2 times per quarter in San Francisco and therefore this person can be situated anywhere in the US. 

 

 

#LI-REMOTE
#LI-AK7

This is a 100% remote position. Applicants may be located in Canada.

Job details & requirements

Occupation
Software Engineer
Openings
1
Open to applicants
Canada