Snorkel AI

1 month ago

Research Scientist - RL Training

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 6 hours agoStatus: Live

Job Summary

Research Scientist focused on reinforcement learning for training and aligning large language models. Work with research and engineering teams to develop data-driven RL methods, reward signals, and RL-ready data products, advancing Snorkel's data-centric training offerings in a fast-paced, high-iteration environment.

Location: Redwood City, San Francisco

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Key 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, verifiable rewards) that customers can use to train and fine-tune large language models.
•Design and build data pipelines that generate high-quality training signal for RL workflows, including AI-assisted data annotation 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-ready data products.
•Stay current with the latest developments in large-scale multi-node LLM training, alignment research, and scalable RL methods (on complex environments such as Terminal-Bench), bringing relevant advances into Snorkel's data-as-a-service approach.

Pay and Benefits

Salary: USD 200,000 - 325,000 annually

Key Requirements

•PhD in machine learning, reinforcement learning, or a related field strongly preferred; exceptional industry experience considered.
•Deep expertise in reinforcement learning from human or AI feedback, reward modeling and credit attribution.
•Experience training or fine-tuning 30B+ large language models at scale, including distributed training infrastructure.
•Strong proficiency in Python and ML frameworks, especially PyTorch and HuggingFace; hands-on experience with RL frameworks such as Verl and SkyRL.
•Solid software engineering fundamentals; ability to build research prototypes that can be run, extended, and integrated into data production workflows.

Experience:AIMachine learningLLMsReinforcement learning

Education:PhD / Doctorate

Skills:Problem-solvingCommunicationCollaborationCritical thinkingAnalytical thinking

Languages:English

Tech Stack:PythonPyTorchHuggingFaceVerlSkyRLAWSGCPKubernetesSlurm

Company Brief

Snorkel AI

Develops a programmatic data labeling platform and tools to accelerate machine learning by enabling teams to generate, manage, and maintain training datasets through weak supervision and automations.

Industry: Data Infrastructure

Company Size: Medium (51 to 250 employees)

Growth: Growth Stage Startup

Funding: Series C

Headquarters: Palo Alto, United States

Founded: 2019

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Snorkel AI

1 month ago

Research Scientist - RL Training

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 6 hours agoStatus: Live

Job Summary

Location: Redwood City, San Francisco

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Key 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, verifiable rewards) that customers can use to train and fine-tune large language models.
•Design and build data pipelines that generate high-quality training signal for RL workflows, including AI-assisted data annotation 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-ready data products.
•Stay current with the latest developments in large-scale multi-node LLM training, alignment research, and scalable RL methods (on complex environments such as Terminal-Bench), bringing relevant advances into Snorkel's data-as-a-service approach.

Pay and Benefits

Salary: USD 200,000 - 325,000 annually

Key Requirements

•PhD in machine learning, reinforcement learning, or a related field strongly preferred; exceptional industry experience considered.
•Deep expertise in reinforcement learning from human or AI feedback, reward modeling and credit attribution.
•Experience training or fine-tuning 30B+ large language models at scale, including distributed training infrastructure.
•Strong proficiency in Python and ML frameworks, especially PyTorch and HuggingFace; hands-on experience with RL frameworks such as Verl and SkyRL.
•Solid software engineering fundamentals; ability to build research prototypes that can be run, extended, and integrated into data production workflows.

Experience:AIMachine learningLLMsReinforcement learning

Education:PhD / Doctorate

Skills:Problem-solvingCommunicationCollaborationCritical thinkingAnalytical thinking

Languages:English

Tech Stack:PythonPyTorchHuggingFaceVerlSkyRLAWSGCPKubernetesSlurm

Company Brief

Snorkel AI

Develops a programmatic data labeling platform and tools to accelerate machine learning by enabling teams to generate, manage, and maintain training datasets through weak supervision and automations.

Industry: Data Infrastructure

Company Size: Medium (51 to 250 employees)

Growth: Growth Stage Startup

Funding: Series C

Headquarters: Palo Alto, United States

Founded: 2019

Website LinkedIn