Senior Software Engineer (Agentic Coding RL Environments)

Role responsibilities

Build coding RL environments and benchmarks to test agent performance on realistic software engineering tasks. Design tasks, review model outputs, and establish success criteria to improve future models.

Requirements

Requires professional experience shipping scaled production systems and expertise in at least one major tech stack. Candidates must possess strong engineering judgment and the ability to work independently.

Key skills

Software Engineering, TypeScript, Python, Ruby, PHP, Java, Rust, Go, C++, Code Review, RL Environments, Benchmarking, Red-teaming, Test Design

Keywords

Agentic Coding, RL Environments, Reinforcement Learning, Benchmarks, Production Systems, TypeScript, Python, Ruby, PHP, Java, Rust, Go, C++, Red-teaming, Software Engineering, Model Evaluation, Frontier Models