Machine Learning Research Scientist (Post-Training)

Scale AI; New York (NY); On-site; USD 150,000 - 200,000; Full time

Benefits offered by this job

Health & wellbeing benefits

Learning & development stipend

Community & ERG events

Parental support

Job summary

Scale AI seeks Research Scientists and Research Engineers to advance LLM post-training techniques (SFT, RLHF, reward modeling). The role emphasizes optimizing data curation and algorithms to improve instruction following, factual accuracy, coding, multilingual and multimodal understanding.

You will develop novel methods, collaborate with researchers, and publish in top conferences. Join Scale AI to help shape the next generation of generative models and work with leading labs on strategic inputs

Qualifications

• Published research in ML at major conferences or journals.
• Deep understanding of DL, RL, and large-scale model fine-tuning.
• Excellent written and verbal communication skills.
• Ph.D. or Master’s in CS/ML/AI or related field.
• Experience in customer-facing roles.
• Experience with post-training techniques such as RLHF or instruction tuning.

Responsibilities

• Develop novel post-training methods to improve LLMs.
• Collaborate with researchers and engineers to set data-driven best practices.
• Optimize data curation and algorithms to boost instruction following, factuality, and multilingual/multimodal understanding.
• Publish findings at top AI conferences and contribute to model robustness.

Skills

Post-training techniques

Reinforcement learning

Deep learning

Communication skills

Customer-facing experience

Education

Ph.D. or Master’s in CS/ML/AI

Job description

• We are looking for Research Scientists and Research Engineers with expertise in LLM post-training (SFT, RLHF, reward modeling)
• This role will focus on optimizing data curation and algorithmic improvements to enhance LLM capabilities in core areas such as instruction following, factuality, coding, multilingual and multimodal understanding
• In this role, you will develop novel methods to improve the alignment and generalization of large-scale generative models
• You will collaborate with researchers and engineers to define best practices in data-driven AI development
• You will also partner with top foundation model labs to provide both technical and strategic input on the development of the next generation of generative AI models
• Research and develop novel post-training techniques, including SFT, RLHF, and reward modeling, to enhance LLM core capabilities in areas of instruction following, factuality, coding, multilingual and multimodal understanding
• Design and experiment new approaches to preference optimization
• Analyze model behavior, identify weaknesses, and propose solutions for bias mitigation and model robustness
• Publish research findings in top-tier AI conferences

Benefits

• Health & Wellbeing: Our holistic approach to supporting Scaliens includes comprehensive health coverage, dental and vision insurance, mental healthcare services, and more. PTO policies and accommodating schedules ensure you’ll get time off when you need it to relax and recharge. Note that our offerings may vary by region as we strive to respond to the unique needs of Scaliens around the globe.
• Personal & Career Growth: Continuously learn and grow through annual learning & development stipend, attending leadership breakfasts, manager training, speaker series, and joining an ERG.
• Building Scale Community: We welcome guests to our offices, and you can expect to see Scalien families and friends around. Join local happy hours, and accept invites to game nights, book clubs, and many other employee-led community events.
• Parental Support: Balancing work and family is essential, and Scale understands the importance of having adequate leave policies in place to promote a healthy home and work life.

Qualifications

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