Research Scientist, Safety Post Training
Scale AI- Location
- San Francisco, California; New York, New York
- Work mode
- On-site
- Type
- full time
- Listed
Applications go directly to Scale AI. Ramai takes no fee for placement and no money for ranking.
[ About this role ]
Research Scientist, Safety Post Training at Scale AI focuses on developing and applying post-training methods and interpretability techniques to enhance the safety and understanding of frontier AI systems. The role involves designing pipelines to study training choices' impact on model safety, developing evaluations to reveal undesirable behaviors, and collaborating to translate findings into safety standards.
Skills and focus areas
- post-training methods
- interpretability techniques
- rlhf
- dpo
- grpo
- machine learning
- generative ai
- ai safety
- ai alignment
- policy research
- evaluation benchmarks
- best practices
Summary written by Ramai from the original posting. Full details and requirements are on Scale AI’s careers page.
[ More at Scale AI ]
Data-centric infrastructure to accelerate the development of AI
See all 170 open roles at Scale AI →[ Similar roles at other startups ]
- Therapeutic Research AssociateEpinoma
- Principal Scientist (pd/msat)Mytos
- General InterestPostEra
- Lab Technician- Quality ControlVolta Labs, Inc.
- Ai Researcherarnata
- Research Engineer - Ai SystemsYotta
[ Not quite right? ]
Tell the assistant what you’re after — stage, location, stack, visa sponsorship — and it searches every open role for you. A few questions are free, no account needed.