Staff Machine Learning Engineer, Conversion Visibility

The Conversion Visibility team enables a performant ads marketplace and helps prove value to advertisers by connecting Pinterest onsite activity with conversions that happen offsite (both digital and physical) in a privacy-preserving way. As a Staff Machine Learning Engineer on this team, you will be the founding ML IC driving identity and conversion signal modeling across our pipeline so advertisers retain accurate, privacy-aware performance visibility as signals fragment and degrade. You will set the technical direction for high-impact ML systems that feed ranking, bidding, measurement, and reporting across Pinterest’s ads stack.

What you’ll do:

• Lead the design and implementation of identity and conversion signal models (e.g., user match prediction, conversion type/value prediction, probabilistic attribution and deduplication) that improve match precision/recall and downstream conversion quality across web and app surfaces.


• Own one or more major identity prediction initiatives end-to-end—from problem framing, label and feature design, and offline evaluation through production deployment and online experimentation.


• Build and evolve ML-powered components in the conversion visibility pipeline, partnering with infra teams to create scalable, low-latency systems for ingesting, enriching, and exposing conversion signals to ranking, bidding, measurement, and reporting stacks.


• Establish ML development best practices (data quality, feature pipelines, evaluation, experimentation) within Conversion Visibility, and mentor engineers so non-ML partners can confidently contribute to ML-powered components.


• Collaborate closely with Ads Ranking & Bidding, Measurement Products, and Conversion Ingestion & Attribution teams to define interfaces, SLAs, and success metrics that ensure identity and signal models plug cleanly into the broader ads ecosystem.


• Use AI to accelerate analysis and iteration on model ideas and architectures, while applying strong judgment, testing, and verification to ensure correctness, reliability, and advertiser trust.


• Apply LLM-powered tools to synthesize experiment results, technical docs, and partner feedback into clear options and recommendations, helping the team explore more approaches and converge on high-impact solutions faster.
  

What we’re looking for:

• Experience building and deploying large-scale ML systems in production (e.g., ads, measurement, recommendation, ranking, or search), with strong end-to-end ownership from problem scoping through evaluation and experimentation, and solid software engineering skills in at least one modern language (e.g., Python, Java) and large-scale data systems.


• Degree in computer science, machine learning, statistics, or related field


• Meaningful hands-on experience or strong familiarity with ads conversion, identity/user matching, or measurement domains, ideally under privacy and signal-loss constraints (e.g., cookies, IP, ATT, SKAN).


• Expertise in probabilistic modeling and measurement (e.g., identity prediction, cohort-to-user inference, modeled conversions, data driven attribution) and in designing trustworthy metrics under noisy or partial labels.


• Proven Staff-level technical leadership as a hands-on IC, setting technical direction and driving multi-quarter ML and systems roadmaps, including aligning stakeholders on priorities, trade-offs, and execution plans.


• Excellent cross-functional communication and collaboration skills, building strong partnerships with product, data science, infra, and partner ML teams to clarify ambiguous problem spaces, co-create solutions, and drive consensus with senior stakeholders.


• Experience using AI coding assistants (e.g., Cursor, Claude Code) and LLM-powered productivity tools to accelerate development, experimentation, and data exploration, with a clear approach to validation, data protection, and critical review of AI-assisted work.
  

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 once per week and therefore needs to be in a commutable distance from one of the following offices: Seattle, San Francisco, Palo Alto.