Home
/
Jobs
/
GenAI Post-Training Scientist (SFT, RLHF, Reward Modeling)
GenAI Post-Training Scientist (SFT, RLHF, Reward Modeling)
Scale AI
FULL_TIME
Remote · US
San Francisco, CA, US
Posted: 2026-05-11
Until: 2026-06-10
Apply Now →
You will be redirected to the original job posting on BeBee.
Apply directly with the employer.
Job Description
A leading AI technology company in San Francisco seeks Research Scientists and Engineers to enhance large-scale generative models. You will research post-training techniques to improve model alignment and generalization while collaborating with industry experts. Ideal candidates possess a Ph.D. or Master’s in relevant fields and a comprehensive understanding of deep learning. The role offers competitive compensation packages and various benefits including health coverage and PTO.