AI Engineer — Reinforcement Learning

Yutori
San Francisco
Workplace: OnsiteFull timeFunction: Data Science & Machine LearningSkills: ["Reinforcement learning","Distributed systems","GPU","NCCL","Multimodal","LLMs"]

Join the founding AI technical staff at Yutori to build a superhuman web-agent and scale large-scale RL infrastructure. You’ll work on distributed async reinforcement learning with multimodal LLMs in web environments, and collaborate with product engineers to translate cutting-edge AI capabilities into elegant, reliable product experiences. You will help shape the stack from training models to end-user interfaces.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Yutori
Yutori
1 year ago

AI Engineer — Reinforcement Learning

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 16 hours agoStatus: Live

Job Summary

Join the founding AI technical staff at Yutori to build a superhuman web-agent and scale large-scale RL infrastructure. You’ll work on distributed async reinforcement learning with multimodal LLMs in web environments, and collaborate with product engineers to translate cutting-edge AI capabilities into elegant, reliable product experiences. You will help shape the stack from training models to end-user interfaces.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Build a superhuman generalist web-agent.
  • •Scale infra, data, algorithms for large-scale distributed async reinforcement learning with multimodal LLMs acting in web environments.
  • •Work closely with product engineers to translate cutting-edge AI capabilities into elegant and reliable product experiences.

Pay and Benefits

Equity and Bonus:Equity
Perks:Visa SponsorshipHealth InsuranceDentalVisionEquityRelocationCommuter BenefitsPaid Leave

Key Requirements

  • •Experience with large-scale RL, ideally for post-training multimodal LLMs.
  • •Experience building distributed systems for RL (balancing trainer, environment, actor workloads).
  • •Experience with ML infrastructure (GPU clusters) and supporting networking (NCCL).
  • •High IQ, high EQ, high agency, high craftsmanship, low ego. Proactive, clear communication.
  • •Strong collaboration skills and ability to translate AI capabilities into product experiences.
Skills:Reinforcement learningDistributed systemsGPUNCCLMultimodalLLMs
Tech Stack:RLDistributed systemsGPU clustersNCCLMultimodal LLMs

Eligibility

Visa:Visa sponsorship
Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

Yutori
Yutori provides an HR-focused platform that helps companies streamline employee benefits, payroll, and wellbeing via integrated software and services, designed to simplify workforce administration and improve employee experience across distributed teams.
Industry: HR Tech
Website