AI Safety & Post-Training Scientist

Scale; San Francisco, New York (CA, NY); On-site; USD 216,000 - 270,000; Full time

Job summary

Scale Labs, a leader in AI safety research, seeks a Research Scientist focused on Safety Post Training to advance post-training methods and interpretability techniques for safer frontier AI systems.

You will design post-training pipelines, study how training choices affect safety and alignment, and collaborate with policymakers, engineers, and researchers to translate findings into safety standards and evaluation benchmarks.

Qualifications

• At least three years of experience addressing sophisticated ML problems, whether in a research setting or in product development.
• Experience with post-training and RL techniques such as RLHF, DPO, GRPO, and similar approaches.
• Strong written and verbal communication skills to operate in a cross-functional team.

Responsibilities

• Develop and apply post-training methods and interpretability techniques to make frontier AI systems safer, and better understood by researchers and policymakers.
• Design and run post-training pipelines to study how training choices affect model safety, robustness, and alignment properties.
• Collaborate with policymakers, engineers, and other researchers to translate post-training and interpretability findings into actionable safety standards, evaluation benchmarks, and best practices.

Skills

Post-training techniques

RL techniques (RLHF, DPO, GRPO)

Generative AI research

3+ years ML experience

Cross-functional communication

Job description

Scale Labs, a leader in AI safety research, seeks a Research Scientist focused on Safety Post Training to advance post-training methods and interpretability techniques for safer frontier AI systems.

You will design post-training pipelines, study how training choices affect safety and alignment, and collaborate with policymakers, engineers, and researchers to translate findings into safety standards and evaluation benchmarks.