Research Engineer — Reinforcement Learning

Firecrawl
San Francisco
Workplace: HybridFull timeUSD 180,000 - 290,000 annuallyFunction: Education & TrainingExperience: 3+ yearsSkills: ["Communication","Collaboration","Problem-solving"]

Build and deploy reinforcement learning pipelines and training infrastructure to improve web data extraction models. You’ll fine-tune models, design reward signals, and bridge LLM-based agents with classical RL, running rapid experiments and communicating results clearly to product and leadership.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Firecrawl
Firecrawl
3 months ago

Research Engineer — Reinforcement Learning

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 15 hours agoStatus: Live

Job Summary

Build and deploy reinforcement learning pipelines and training infrastructure to improve web data extraction models. You’ll fine-tune models, design reward signals, and bridge LLM-based agents with classical RL, running rapid experiments and communicating results clearly to product and leadership.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: Education & Training

Key Responsibilities

  • •Build training infrastructure and reward pipelines from scratch, design and operate data collection, reward modeling, training runs, evaluation, and deployment
  • •Fine-tune foundation models to achieve state-of-the-art results for web data extraction and structured output generation
  • •Bridge LLM agents and classical RL, designing reward signals and applying RL methods to multi-step agent workflows
  • •Run fast experiments, test meaningful hypotheses, and iterate quickly to inform product decisions
  • •Communicate results clearly to engineers, product, and leadership, translating RL work for non-RL stakeholders

Pay and Benefits

Salary: USD 180,000 - 290,000 annually
Equity and Bonus:Equity
Perks:EquityRemote WorkPaid LeaveLearning Budget401k

Key Requirements

  • •3+ years in applied reinforcement learning, ML engineering, or model training with production systems
  • •Experience building training infrastructure and reward pipelines
  • •Experience fine-tuning models to state-of-the-art results
  • •Production deployment experience and balancing model quality, latency, and cost
  • •US Citizenship/Visa required for SF location; Remote eligible otherwise
Experience:3+ yearsAIMLNLPWeb data extractionLLMs
Skills:CommunicationCollaborationProblem-solving
Tech Stack:Reinforcement learningPPORLHFLLMsGPU clustersProduction deployment

Eligibility

Visa:US Citizenship/Visa
Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

Firecrawl
example.com is an IANA-reserved domain maintained for use in documentation, examples, and testing. It is not an operating commercial company and exists solely to provide a stable, non-resolvable hostname for illustrative purposes.
Industry: Other
Website