Responsible AI Evaluation Engineer for Gen AI Safety

Apple; Cupertino (CA); Presencial; USD 185.000 - 325.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Med and dental coverage

Retirement benefits

Product discounts

Descripción de la vacante

Apple seeks a talented professional to own and scale Responsible AI evaluation for global gen‑AI products. You will turn safety and inclusivity policy into measurable metrics and repeatable pipelines.

You will design evaluation datasets, combine human annotation with auto-grading, and build data pipelines for end-to-end safety assessments, collaborating across teams to accelerate safe releases. Strong data science and Python/Pandas skills are essential.

Formación

• MS or PhD in Computer Science, Linguistics, Cognitive Science, HCI, Psychology, Mathematics, Physics, or related field with strong data collection/analysis
• BA/BS with 8+ years relevant work experience, including 2+ years directly managing engineering teams
• Experience in responsible AI, safety/fairness in generative models, and diverse teams
• Experience gathering/analyzing varied language, image, voice, video, and multi-modal data
• Proficiency in data science, analytics, Python & Pandas, and AI-assisted coding tools

Responsabilidades

• Develop evaluation metrics for safety and fairness risks in gen‑AI features
• Design datasets and scaling coverage with human and synthetic generation
• Create sampling strategies combining human annotation with auto-grading
• Implement data pipelines and collaborate cross-functionally for end-to-end safety evaluations
• Automate workflows to improve evaluation velocity and throughput
• Distill evaluation findings for product engineering and safety policy teams
• Work with sensitive content in a controlled, compliant manner

Conocimientos

Responsible AI

Multimodal models

LLM-Judges

Human-in-the-loop

Data science

Python

Pandas

Cross-functional collaboration

Experiment design

Publications

Educación

MS or PhD in Computer Science, Linguistics, Cognitive Science, HCI, Psychology, Mathematics, Physics (or related)

BA/BS with 8+ years relevant experience, including 2+ years managing eng teams

Herramientas

Python

Pandas

Descripción del empleo

Apple seeks a talented professional to own and scale Responsible AI evaluation for global gen‑AI products. You will turn safety and inclusivity policy into measurable metrics and repeatable pipelines.

You will design evaluation datasets, combine human annotation with auto-grading, and build data pipelines for end-to-end safety assessments, collaborating across teams to accelerate safe releases. Strong data science and Python/Pandas skills are essential.