jobs

Machine Learning Research Scientist, Post-Training

Scale works with the industry’s leading AI labs to provide high quality data and accelerate progress in GenAI research. We are looking for Research Scientists and Research Engineers with expertise in LLM post-training (SFT, RLHF, reward mod

In inglese

Company

Scale AI

Location

San Francisco, CA; Seattle, WA; New York, NY

Status

Open

Posted

2025-02-11T05:40:13+00:00

Scale AI is hiring research scientists and engineers for LLM post-training, focused on SFT, RLHF and reward modeling. The work covers new post-training techniques, preference optimization, data curation and evaluation for text and multimodal models, and analyzing model behavior for bias mitigation and robustness. Findings are meant for top-tier conferences, and the role includes technical and strategic input to foundation model labs. The posting asks for a Ph.D. or master's, deep learning and reinforcement learning depth, published research, and prior customer-facing experience. Onsite in San Francisco, Seattle or New York.