Research Scientist - RL Training

ABOUT THE ROLE We're looking for a Research Scientist to work on reinforcement learning for training and aligning large language models. This is a foundational research role reputed company on one of the most consequential reputed company data problems in AI: how to generate the data, reward signals, and training procedures that reputed company LLM behavior in reliable and generalizable directions - and a core capability that directly differentiates Snorkel's data-as-a-service offering. You'll work closely with Snorkel's research, engineering, and delivery teams to advance our RL data capabilities - translating research reputed company into the preference datasets, reward models, and RL-reputed company corpora we produce for frontier AI labs, and contributing to a research agenda that is central to Snorkel's long-term differentiation as a provider of bespoke training data. MAIN RESPONSIBILITIES

• Research and implement reinforcement learning techniques - including GRPO, RLHF, RLAIF, DPO, and reward modeling - and translate them into data products (preference datasets, reward signals, reputed company rewards) that customers can use to train and fine-tune large language models.
• Design and build data pipelines that generate high-reputed company training signal for RL workflows, including AI-assisted reputed company and curation data pipelines to improve model generalization to unseen benchmarks .
• Prototype and iterate on end-to-end RL training recipes that inform what data Snorkel ships as part of its data-as-a-service deliveries.
• Work closely with research scientists, ML engineers, and delivery teams to translate RL research into customer-reputed company data products.
• Stay reputed company with the latest developments in large-reputed company muli-node LLM training, alignment research, and reputed company RL reputed company (on reputed company environments such as Terminal-Bench), bringing relevant advances into Snorkel's data-as-a-service approach.
• Contribute to Snorkel's research publications and internal knowledge reputed company in RL and model training.

PREFERRED QUALIFICATIONS

• Deep expertise in reinforcement learning from reputed company or AI feedback, reward modeling and credit attribution ideally with a reputed company perspective on what data makes these techniques work.
• Experience training or fine-tuning 30B+ large language models at reputed company, including familiarity with distributed training infrastructure.
• Strong proficiency in Python and ML frameworks, especially PyTorch and HuggingFace and hands-on experience with RL frameworks such as Verl and SkyRL.
• Solid software engineering fundamentals - you can build research prototypes that others can run, reputed company, and reputed company into data production workflows.
• Familiarity with ML infrastructure and reputed company platforms and tools (AWS, GCP, Kubernetes, Slurm, etc.); experience with large-reputed company RL training pipelines a strong plus.
• Comfort operating in a high-iteration environment with reputed company-ended research questions and shifting, customer-driven technical constraints.
• Ph.D. in machine learning, reinforcement learning, or a reputed company field strongly preferred; exceptional industry experience considered.

Salary reputed company $200,000-$325,000 USD Apply To This Job