Lead ML Research Engineer — Safe Foundation Models

Apple Inc.; Seattle (WA); On-site; USD 175,000 - 309,000; Full time

Job summary

Apple Inc. in Seattle, WA is seeking a Senior ML Research Engineer focusing on AFM Safety to advance safe and reliable foundation models for Apple products.

You will lead research on agentic safety, model character and persona, and multimodal safety across audio and vision, collaborating with ML researchers, engineers, and product teams. The role emphasizes safety and responsibility in large language models with strong publication records and hands-on ML experience, contributing to privacy and

Qualifications

• Strong ML background with hands-on training and publications.
• Proficient in working with real-world codebases.
• Experience with LLMs and post-training safety preferred.

Responsibilities

• Define and deliver safety methods for foundation models, focusing on agentic safety, model character and persona, and multimodal safety (audio and vision).
• Research safety and security risks of agentic systems, including tool use, and develop data/evaluations to address them.
• Help define and safeguard the model's character and persona for consistent, safe behavior across contexts.
• Build methods to train/evaluate foundation models with safety in mind for audio/vision modalities.
• Research/Improve safety alignment and robustness for large language models.
• Collaborate with engineers/researchers across teams to improve Apple products.
• Partner with product teams to define requirements and drive quality and delivery.

Skills

ML research

Coding skills

Collaborations

Safety in ML

Education

BS/MS/PhD in CS/ML or related

Job description

Apple Inc. in Seattle, WA is seeking a Senior ML Research Engineer focusing on AFM Safety to advance safe and reliable foundation models for Apple products.

You will lead research on agentic safety, model character and persona, and multimodal safety across audio and vision, collaborating with ML researchers, engineers, and product teams. The role emphasizes safety and responsibility in large language models with strong publication records and hands-on ML experience, contributing to privacy and