Research Scientist, Safety Post Training

Scale Labs

San Francisco, CA, US
Base: $216,000 - $270,000 usd; equity: included ba...
On-site
Experience with rlhf dpo grpo post-training techniques
Track record of published research in generative ai
Three years experience addressing sophisticated ml problems
The role focuses on developing post-training pipelines to study how training choices affect model safety, robustness, and alignment properties

Job Summary

  • The role focuses on developing post-training pipelines to study how training choices affect model safety, robustness, and alignment properties.
  • Candidates will collaborate with policymakers, engineers, and researchers to translate findings into actionable safety standards and evaluation benchmarks.
  • Compensation includes a base salary range of $216,000 to $270,000 USD along with equity, comprehensive health benefits, and a learning stipend.

Matching Summary

The role focuses on developing post-training pipelines to study how training choices affect model safety, robustness, and alignment properties.

Salary

Base: $216,000 - $270,000 USD; Equity: Included based on Board approval; Benefits: Comprehensive health, dental, vision, retirement, PTO, and learning stipend

Skills & Requirements

Must-have

  • Experience with RLHF DPO GRPO post-training techniques
  • Track record of published research in generative AI
  • Three years experience addressing sophisticated ML problems

Nice-to-have

  • Experience with mechanistic interpretability or probing
  • Familiarity with red-teaming adversarial evaluation
  • Understanding of reward hacking sycophancy alignment faking

Key Requirements

  • At least three years of experience in ML research or product development
  • Published research track record in machine learning and generative AI
  • Strong written and verbal communication skills for cross-functional teams

Work Rights

Not specified

Tailored Resume

Cover Letter