← All roles

Senior Software Engineer: Agentic Coding RL Environments

Apply on company site
Remote$100/hr - $150/hrcontractPosted 2mo ago

About the role

Frontier labs train and evaluate coding agents on RL environments and benchmarks you’ll build. Fully remote contractor role focusing on designing and implementing RL environments and benchmarks for agentic coding in real software engineering tasks.

Responsibilities

  • Design tasks based on real engineering work
  • Reviewing and red-teaming model output
  • Writing tests, rubrics, and success criteria
  • Giving structured feedback that improves future models
  • Build coding RL environments and benchmarks that test how agents perform on realistic software engineering tasks
  • Develop environments that are used to train, evaluate, and compare frontier coding models

Qualifications

  • Professional software engineering experience shipping real, scaled production systems
  • Strong judgment about what constitutes good code and model failures
  • Comfort working independently and giving technical feedback
  • Expertise in at least one common tech stack (e.g., TypeScript, Python, Ruby, PHP, Java, Rust, Go, or C++)
  • No prior AI/ML experience required; strong engineering judgment and attention to detail are key

Skills

Required:Software engineering experienceTechnical judgment on code quality and model failuresIndependent work and technical feedbackProficiency in at least one tech stack (TypeScript, Python, Ruby, PHP, Java, Rust, Go, C++)

Benefits

  • Fully remote
  • Choose your own schedule
  • Guaranteed projects
  • Competitive pay: $100–$150+/hour; rates scale with experience
Last updated Sep 30, 2026. Interested? Apply on the company site.

About Surge AI

Human Intelligence for AGI

Our mission is to raise AGI with the richness of human intelligence — curious, witty, imaginative, and full of unexpected brilliance.

AGIArtificial Intelligenceliquid-ai-recruiting-target

More open roles at Surge AI