Post-Training ML Research Scientist (RLHF/SFT)

Scaleai; New York, San Francisco (NY, CA); On-site; USD 181,000 - 226,000; Full time

Benefits offered by this job

Health coverage

Equity

Generous PTO

Learning & development stipend

Commuter stipend

Job summary

Scale is seeking Research Scientists and Research Engineers to advance LLM post-training techniques for text and multimodal data. You will collaborate with researchers and engineers to define data-driven best practices, and partner with leading labs to shape the next generation of generative AI models.

Ideal candidates hold a PhD or Master’s in CS/ML, with strong background in deep learning, RL, and post-training methods such as RLHF.

Qualifications

• PhD or Master’s degree in Computer Science, Machine Learning, AI, or related field.
• Deep understanding of deep learning, reinforcement learning, and large-scale model fine-tuning.
• Experience with post-training techniques such as RLHF, preference modeling, or instruction tuning.
• Excellent written and verbal communication skills.
• Published research in ML at major conferences (NeurIPS, ICML, ICLR, ACL, EMNLP, CVPR) and/or journals.
• Previous experience in a customer facing role.

Responsibilities

• Research and develop novel post-training techniques to enhance LLM core capabilities in text and multimodal modalities.
• Design and experiment with preference optimization approaches.
• Analyze model behavior and propose bias mitigation and robustness solutions.
• Publish research findings in top-tier AI conferences.

Skills

LLM post-training

Reinforcement learning

Deep learning

RLHF

Preference modeling

Instruction tuning

Communication

Research publications

Education

PhD or Master’s

Machine Learning background

Job description

Scale is seeking Research Scientists and Research Engineers to advance LLM post-training techniques for text and multimodal data. You will collaborate with researchers and engineers to define data-driven best practices, and partner with leading labs to shape the next generation of generative AI models.

Ideal candidates hold a PhD or Master’s in CS/ML, with strong background in deep learning, RL, and post-training methods such as RLHF.