✦ Luna Orbit — Software Engineering

Full Stack Software Engineer, Reinforcement Learning

at Anthropic

📍 San Francisco, CA Hybrid Posted March 07, 2026
Apply Now → ← Browse All Jobs

Position Details

Type Full-Time
Experience mid
Exp. Years Entry to Mid-level
Education Not specified
Category Software Engineering

About this role

Full-Stack Software Engineer role focused on developing platforms and tools for reinforcement learning research, data collection, and training observability.

Key Responsibilities

  • Build web platforms for RL environments
  • Develop vendor interfaces
  • Create data collection tools
  • Design evaluation dashboards
  • Ensure platform reliability

Technical Overview

Involves building web-based platforms, APIs, data pipelines, and dashboards to support AI research and model training workflows.

Ideal Candidate

The ideal candidate is a mid-level full-stack software engineer with strong skills in building web platforms, APIs, and data pipelines, with an interest or experience in reinforcement learning and AI systems.

Must-Have Skills

Strong full-stack engineering skillsExperience building web platformsAbility to develop APIs and UIsExperience with data collection and evaluation tools

Nice-to-Have Skills

Experience with reinforcement learningKnowledge of AI systemsExperience with training data pipelines

Tools & Platforms

Web PlatformsAPIsData PipelinesEvaluation Dashboards

Required Skills

Full-Stack DevelopmentWeb PlatformsAPIsData PipelinesEvaluation DashboardsObservabilityReinforcement LearningTraining Environments

Hard Skills

Full-Stack DevelopmentWeb PlatformsAPIsVersioningUI/UXData PipelinesEvaluation DashboardsObservabilityReinforcement LearningTraining Environments

Soft Skills

Problem-solvingCollaborationReliabilityFast-paced environment adaptationCommunication

Industry & Role

Industry AI & Machine Learning
Job Function Developing scalable software platforms for reinforcement learning research and training

Keywords for Your Resume

Full Stack Software EngineerReinforcement LearningWeb PlatformsAPIsData PipelinesEvaluation DashboardsObservabilityTraining EnvironmentsData CollectionUI/UXBackend ServicesVersioningReliabilityFast-paced environment

Deal Breakers

Lack of full-stack engineering experience, No experience with web platform development, Inability to develop APIs or UIs, Lack of interest or experience in reinforcement learning

Apply for this Position →

Get matched to jobs like this

Luna finds roles that fit your skills and career goals — no endless scrolling required.

Create a Free Profile