Research Scientist – RL Training

Snorkel AI

. Research and implement reinforcement learning techniques, including GRPO, RLHF, RLAIF, DPO, and reward modeling .

Posted 11/9/2026full-timeUnited StatesMid-LevelSenior💰 $200,000 - $350,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates deep expertise in reinforcement learning techniques, including reward modeling and training large language models, while effectively collaborating with cross-functional teams to deliver customer-ready data products.

Highest-signal resume keywords

Reinforcement Learning TechniquesLarge Language Model TrainingPython ProficiencyDistributed Training InfrastructureML Frameworks (PyTorch, HuggingFace)

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Reinforcement LearningReward ModelingCredit AttributionData Pipeline DevelopmentAI-Assisted Data AnnotationTraining Signal GenerationSoftware Engineering FundamentalsLarge-Scale RL Training PipelinesHigh-Iteration Environment AdaptabilityResearch Publication Contribution

Soft Skills

CollaborationAdaptabilityProblem-Solving

Tools & Technologies

AWSGCPKubernetesSlurmVerlSkyRL

Certifications & Qualifications

Ph.D. in Machine LearningPh.D. in Reinforcement Learning

Industry Keywords

Data-as-a-ServiceModel GeneralizationMulti-Node LLM TrainingAlignment ResearchScalable RL Methods

Tech Stack

Tools & technologies

AWSCloudGoogle Cloud PlatformKubernetesNode.jsPythonPyTorch

About the role

Key responsibilities & impact

Research and implement reinforcement learning techniques, including GRPO, RLHF, RLAIF, DPO, and reward modeling
Translate RL techniques into preference datasets, reward signals, and verifiable rewards for large language model training and fine-tuning
Design and build data pipelines generating high-quality training signals for RL workflows
Develop AI-assisted data annotation and curation pipelines to improve model generalization to unseen benchmarks
Prototype and iterate on end-to-end RL training recipes
Inform the data products Snorkel ships through its data-as-a-service deliveries
Collaborate with research scientists, ML engineers, and delivery teams to translate RL research into customer-ready data products
Track developments in large-scale multi-node LLM training, alignment research, and scalable RL methods
Contribute to research publications and the internal knowledge base in RL and model training

Requirements

What you’ll need

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
Familiarity with 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
Familiarity with ML infrastructure and cloud platforms and tools such as AWS, GCP, Kubernetes, and Slurm
Experience with large-scale RL training pipelines is a strong plus
Comfort operating in a high-iteration environment with open-ended research questions and shifting, customer-driven technical constraints
Ph.D. in machine learning, reinforcement learning, or a related field strongly preferred; exceptional industry experience considered

Benefits

Comp & perks

Meaningful opportunities to shape priorities and initiatives
Opportunity to influence key strategic decisions
Direct impact on company success
Support for deepening technical expertise
Leadership opportunities
Opportunities to learn new skills across multiple functions
Career growth, learning, and shared success environment
Equal employment opportunities
Reasonable accommodation for individuals with disabilities