Pinterest - San Francisco, CA

posted 4 months ago

Full-time - Senior
San Francisco, CA
Professional, Scientific, and Technical Services

About the position

Pinterest is a platform where millions of people come to find new ideas every day, and our mission is to help them discover inspiration and create a life they love. As a Staff Machine Learning Engineer focused on Search Quality, you will play a crucial role in enhancing the Pinterest search experience, ensuring it is fast, personalized, and relevant for billions of monthly searches. This position is part of the Search Quality team, which is dedicated to improving the search functionality through innovative machine learning solutions. You will be challenged to design and build machine learning models that understand user intent and deliver the most relevant pins to our users. This role offers the opportunity to work on large-scale low-latency systems and state-of-the-art machine learning models, significantly impacting both our users and business metrics. In this position, you will utilize state-of-the-art modeling techniques to enhance Pinterest search capabilities. You will be responsible for improving the efficiency and reliability of large-scale data processing and machine learning inference pipelines. Additionally, you will optimize our serving systems to enhance latency, capacity, and stability while reducing infrastructure costs. This role requires collaboration with product managers and designers to ship machine learning-driven user-facing products, ensuring that the solutions you develop align with user needs and business goals. Pinterest promotes a progressive work model called PinFlex, which allows for flexibility in how and where you work. This role is remote, and while it does not offer relocation assistance, it provides a unique opportunity to contribute to a platform that inspires creativity and innovation.

Responsibilities

  • Design and build ML models that understand user intent and deliver the most relevant pins.
  • Utilize state-of-the-art modeling techniques to improve Pinterest search.
  • Improve the efficiency and reliability of large-scale data processing and ML inference pipelines.
  • Optimize our serving systems to improve latency, capacity, and stability and reduce infrastructure costs.

Requirements

  • 5+ years experience with Recommender system or User modeling, implementing production ML systems at scale.
  • 5+ years experience with large-scale distributed backend service.
  • Experience with building deep neural net models, including architecture design, training, and evaluation.
  • Experience in working with Generative AI models.
  • Languages: Python, Java.
  • Machine Learning: PyTorch, TensorFlow.
  • Big data processing: Spark, Hive, MapReduce.
  • Experience in closely collaborating with product managers/designers to ship ML-driven user-facing product.

Benefits

  • Equity eligibility
  • Base salary range of $166,694-$342,844 USD based on various factors including location and experience.
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service