Responsible AI & Safety ML Engineer — Evaluation Lead

Apple, Inc.; Cupertino (CA); Sur place; USD 185 000 - 325 000; Plein temps

Avantages offerts par ce poste

Medical and dental coverage

Retirement benefits

Discounted products and services

Tuition reimbursement

Bonuses or commission

Résumé du poste

Apple Inc. seeks a visionary Engineering Manager to build and lead a team for Responsible AI Evaluation of generative features. You will set technical direction, design datasets, and implement data pipelines to deliver scalable safety insights.

You will work hands-on with evaluation results, conduct failure investigations, and mentor a diverse team to deliver trusted AI experiences globally.

Qualifications

• MS or PhD in Computer Science, Linguistics, Cognitive Science, HCI, Psychology, Mathematics, Physics, or related field with strong basis in scientific data collection and analysis and at least 4 years of relevant work experience, or BA/BS with 8+ years of relevant work experience, with 2+ years directly managing engineering teams.
• Experience gathering and analyzing varied language, image, voice, video, and/or multi‑modal data, including human- and LLM-generated data.
• Experience with LLM-Judges and human-in-the-loop techniques, including designing human annotation projects, writing guidelines, and handling highly multi-labeled data.
• Proficiency in data science, machine learning, analytics, programming with Python & Pandas, and AI-assisted coding tools; experience with plotting/visualisation libraries.
• Cross-functional collaboration to prioritize projects, set schedules, and communicate with all levels and stakeholders.
• Rigorous approach to metric development, interpretation of experiments, and presenting to executives.
• Comfortable leading a team that works with sensitive or potentially offensive content.

Responsabilités

• Develop metrics for evaluation of safety and fairness risks in generative models and Gen‑AI features.
• Design datasets and data needs; expand data coverage with human and synthetic generation methods.
• Develop sampling strategies; combine human annotation with auto-grading for high-quality insights at scale.
• Implement data pipelines and collaborate cross-functionally for end-to-end safety evaluations.
• Automate workflows, increase evaluation velocity, and scale infrastructure for rapid product releases.
• Distill findings into actionable insights for product engineering and safety policy.
• Work with sensitive content exposure as part of risk assessment.

Connaissances

Leadership experience

Responsible AI

Data analysis

Model evaluation

Cross-functional collaboration

Formation

MS/PhD in CS or related field

Outils

Python

Pandas

Plotting libraries

AI-assisted coding tools

Description du poste

Apple Inc. seeks a visionary Engineering Manager to build and lead a team for Responsible AI Evaluation of generative features. You will set technical direction, design datasets, and implement data pipelines to deliver scalable safety insights.

You will work hands-on with evaluation results, conduct failure investigations, and mentor a diverse team to deliver trusted AI experiences globally.