Senior Software Engineer – Agentic RL Environments (Remote)

Surge AI; Greater London; On-site; GBP 101,000 - 152,000; Full time

Job summary

Surge AI is seeking a Senior Software Engineer (Agentic Coding RL Environments) for a fully remote contract role. You will build coding RL environments and benchmarks, design tasks based on real engineering work, and review model outputs to surface meaningful failures. Strong code judgment and independent work are essential.

Open to engineers across time zones with a commitment of 20–40+ hours per week. Compensation ranges from $100–150+ per hour, with higher earnings possible depending on

Qualifications

• Professional software engineer with production-grade shipping experience.
• Expertise in at least one of TypeScript, Python, Ruby, PHP, Java, Rust, Go, or C++.
• Strong judgment of what constitutes good code and meaningful model failure.
• Comfort working independently with direct, code-review-style feedback.
• Availability for a meaningful commitment (20 to 40+ hours per week).

Responsibilities

• Build coding RL environments and benchmarks testing agent performance on realistic software tasks.
• Design tasks based on real engineering work.
• Review and red-team model outputs to surface failures.
• Write tests, rubrics, and success criteria to distinguish good work from poor.
• Provide structured feedback to improve future models.

Skills

TypeScript

Python

Go

C++

Independent work

20–40+ hours per week

Tools

Git

Job description

Surge AI is seeking a Senior Software Engineer (Agentic Coding RL Environments) for a fully remote contract role. You will build coding RL environments and benchmarks, design tasks based on real engineering work, and review model outputs to surface meaningful failures. Strong code judgment and independent work are essential.

Open to engineers across time zones with a commitment of 20–40+ hours per week. Compensation ranges from $100–150+ per hour, with higher earnings possible depending on