Pinterest is a platform where millions of people find creative ideas and plan for memories.
The AI Platform team delivers essential tools and infrastructure utilized by hundreds of AI and ML engineers across Pinterest.
Responsibilities
Shape and scale Pinterest’s AI/ML evaluation platform into a unified, reliable system adopted company-wide.
Identify modernization opportunities, elevate the roadmap, and execute technical strategy for a durable evaluation system for GenAI and ML workloads.
Partner across engineering, research, product, and safety to improve quality, launch decisions, and trust in AI-powered experiences.
Define cross-team technical strategy, align partner teams, and drive broad adoption of shared evaluation capabilities.
Make durable architectural decisions that improve the user experience and reliability of Pinterest’s AI/ML evaluation platform.
Establish evaluation methodologies and standards that balance automated metrics, expert judgment, human feedback, safety, and business outcomes.
Lead complex cross-team workstreams, resolve technical tradeoffs and risks, and deliver impact.
Requirements
3+ years of deep, hands-on experience designing and operating evaluation systems for GenAI and complex ML systems, including benchmark design, golden datasets, automated metrics, human evaluation, model-based grading, and failure analysis.
Strong programming skills in Python coupled with a solid grasp of distributed systems principles.
Deep familiarity with GenAI and RecSys evaluation libraries and frameworks, AutoEvals, OpenEvals, Ragas, etc.
5+ years of experience building scalable platforms for distributed experimentation, data and model versioning, orchestration, observability, release management, and production monitoring.
Strong judgment around GenAI risks, including robustness, bias, privacy, security, and the limitations of automated evaluation signals.
Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent experience.
Conditions
This role will need to be in the office for in-person collaboration 1-2 times/quarter and therefore can be situated anywhere in the country.
This position is not eligible for relocation assistance.
The base salary range for this position is $208,592 - $429,454 USD.