ML Researcher - Posttraining is open at Krea in San Francisco. The posting gives no salary; similar roles in the United States advertise a median of $172K. Posted on Sep 1, 2026, and still on Krea’s careers page when we last checked, on Nov 14, 2026.
About the role
Finetune diffusion models at scale to improve image aesthetics and quality. - Implement posttraining techniques ranging from supervised finetuning, preference optimization, reinforcement learning, on-policy distillation, and various distillation / acceleration techniques. - Design comprehensive eval suites and reward designs for the reinforcement learning stage focused on image space. - Train custom VLM as reward…
The opening lines of the posting. The rest is on Krea’s careers page.
Hiring at Krea
Krea has 13 open roles right now. Most are in Engineering, Design and Data & Research. See all its roles