Data Scientist II

About The Company Pinterest is a global platform that inspires millions of users worldwide to explore creative ideas, envision new possibilities, and plan for memorable moments. Our mission is to bring everyone the inspiration to create a life they love, which is driven by a passionate team dedicated to innovation and inclusivity. At Pinterest, we foster a collaborative environment that values diverse perspectives, creativity, and continuous learning. Our platform is a hub for discovering and sharing ideas across various interests, from home decor and fashion to recipes and travel. We leverage cutting-edge technology, including artificial intelligence, to enhance user experience and deliver personalized content. Our commitment to fostering a positive and dynamic workplace makes Pinterest a great place to grow your career while making a meaningful impact on a global community. About The Role We are seeking a highly skilled Data & Applied Scientist to join our team and drive significant advancements in our machine learning (ML) capabilities. This role focuses on developing and implementing innovative systems for ML measurement, feature understanding, and causal inference at scale. The ideal candidate will have a strong background in ML research, software engineering, and platform development, with a passion for building scalable tools that empower teams across Pinterest. You will translate research-grade workflows into robust production pipelines, apply causal inference methods to address complex measurement challenges, and collaborate closely with engineering and product teams to enhance our ML infrastructure. Your work will directly impact the quality of models, platform efficiency, and the overall effectiveness of Pinterest’s AI-driven features. This is an exciting opportunity to contribute to foundational innovations that elevate the entire ML organization and shape the future of data-driven decision-making at Pinterest. Qualifications 2+ years of hands-on experience as an applied scientist, ML engineer, research scientist, or software engineer with significant ML production experience.Strong proficiency in Python, with experience in PyTorch or equivalent deep learning frameworks.Familiarity with distributed compute frameworks such as Spark or Ray, with Ray experience being a strong plus.Experience with workflow management tools like Airflow, Prefect, Jenkins, or similar for reliable ML pipeline orchestration.Bachelor’s or Master’s degree in Computer Science, Data Science, or a related field, or equivalent practical experience.Deep understanding of ML theory and principles, enabling reasoning about models from first principles.Proficiency in software development best practices, including version control, code review, and reproducible ML pipelines.Ability to build and maintain scalable tools and platforms that enhance the impact of ML teams. Responsibilities Translate research-grade data science workflows, such as proxy metrics and staleness models, into scalable production ML pipelines using tools like Airflow, WandB, and Ray.Apply and productionize causal inference techniques, including propensity scoring, inverse probability weighting (IPW), and targeted maximum likelihood estimation (TMLE), to address high-stakes measurement challenges beyond experimental methods.Develop self-serve tooling to enable non-experts to derive rigorous causal insights at scale, fostering democratization of data science capabilities.Partner with machine learning engineers and product teams to identify opportunities for improving tooling, metrics, and measurement methods, thereby enhancing model quality and business outcomes.Leverage Pinterest’s rich metadata and engagement signals to build data-driven frameworks for feature importance, content deindexing, and platform efficiency improvements.Design, build, and maintain centralized ML platform tools that support feature and model creation, evaluation, and trust, ensuring daily operations at scale