Skip to main contentA logo with &quat;the muse&quat; in dark blue text.

Senior Manager of Meta Evaluation & Quality Assurance

Yesterday Seattle, WA

Apple Services Engineering (ASE) powers many AI and LLM features across App Store, Music, Video and more. As these systems increasingly rely on human-in-the-loop evaluation systems, the quality of our decisions is constrained by the quality of our evaluation systems. We believe that to build exceptional LLMs, you need exceptional mechanisms to validate the signals used to train and evaluate them.

Description

As the Senior Manager of Meta Evaluation & Quality Assurance, you will lead a specialized team of Data Scientists and Machine Learning Engineers who evaluate the evaluators. You will move beyond basic validation to lead the strategy and technical development of ML-based validation frameworks and automated data quality validation pipelines. You will set strategy, guide execution, and work cross functionally to deliver a cohesive quality system that combines machine learning with human-in-the-loop processes to ensure our metrics are trustworthy, robust, and decision-ready.","responsibilities":" Lead, mentor, and develop a multidisciplinary team of Data Scientists and Machine Learning Engineers, fostering a culture of rigorous scientific inquiry, technical excellence, and accountability.

Define and drive the strategic roadmap for Meta Evaluation methodology and standards across Apple Services.

Want more jobs like this?

Get jobs in Seattle, WA delivered to your inbox every week.

Job alert subscription


Oversee the development of ML-based quality validation systems. You will guide ML Engineers in building models that utilize human-in-the-loop workflows to audit evaluators, identifying anomalies, disagreement, and ambiguity in evaluation data.

Establish data quality validation standards and define the statistical processes for measuring confidence, calibration, and inter-rater reliability.

Partner with Model Engineering and Data Science teams to validate new AI Judges (autograders) and Agents pre-production, ensuring they meet prescribed performance standards before deployment.

Collaborate with Operations teams to build active learning loops where human experts adjudicate discrepancies flagged by your validation models, creating a continuous cycle of system improvement.

Monitor the health of the evaluation ecosystem, identifying risks such as evaluator drift, bias, or silent agent failures, and reporting decision-readiness signals to leadership.

Stay current with industry best practices in evaluation science, active learning, and hybrid human-AI quality control, bringing innovative validation methods to Apple's evaluation stack.

This is a highly collaborative leadership position that requires working across Engineering, Quality, Training, and Production Ops. Most of all, you are able to manage and lead change effectively while maintaining Apple culture and standards. Interpersonal skills, strategic thinking, and technical product knowledge are essential for success in this role.

Preferred Qualifications

PhD in Statistics, Computer Science, Machine Learning, or related field

Deep understanding of evaluation pipelines, calibration techniques, and statistical process control

Experience building ML models specifically designed for quality estimation, anomaly detection, or disagreement modeling

Proficiency in Python or R for statistical analysis and reasoning about evaluation data

Experience defining governance gates or certification processes for AI systems

Proven ability to manage complex methodological and technical programs in dynamic, fast-paced environments.

Exceptional communication, organizational, and analytical skill.

Minimum Qualifications

8+ years of experience in Data Science, Machine Learning, or Evaluation Science, with 3+ years leading technical teams

Strong background in Meta Evaluation, AI/ML measurement, statistics, or quality assurance methodologies.

Demonstrated success in designing Human-in-the-Loop (HITL) machine learning systems or active learning pipelines.

Masters degree in Statistics, Data Science, Machine Learning or related field.

Apple is an equal opportunity employer that is committed to inclusion and diversity. We seek to promote equal opportunity for all applicants without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, Veteran status, or other legally protected characteristics. Learn more about your EEO rights as an applicant .

Client-provided location(s): Seattle, WA
Job ID: apple-200641736-3337_rxr-660
Employment Type: OTHER
Posted: 2026-01-30T19:12:46

Perks and Benefits

  • Health and Wellness

    • Parental Benefits

      • Work Flexibility

        • Office Life and Perks

          • Vacation and Time Off

            • Financial and Retirement

              • Professional Development

                • Diversity and Inclusion

                  Company Videos

                  Hear directly from employees about what it is like to work at Apple.