Software Engineer

We are looking for AI Coding Experts to design and build complete, Dockerized Reinforcement Learning Environments (RLEs) used to evaluate and train AI coding agents. This is a hands-on engineering role focused on building realistic coding scenarios, reference solutions, verifiers, and test harnesses. It is not a prompt-writing or data-annotation role.

Responsibilities:

• Design realistic, self-contained Dockerized coding scenarios from scratch.
• Build repository fixtures and clear task instructions for AI coding agents.
• Write working Python reference solutions that demonstrate the correct implementation.
• Develop deterministic verifiers, pytest harnesses, and evaluation logic.
• Review AI-agent trajectories to identify where and why an agent failed.
• Validate whether solutions represent genuine fixes rather than superficial patches.
• Revise and improve scenarios based on structured quality-review feedback.
• Ensure environments are reproducible, offline, and technically reliable.

Requirements:

• Strong hands-on Python development skills.
• Experience writing real software, including reference solutions and automated tests.
• Strong proficiency with Docker and containerised development environments.
• Good understanding of software security and vulnerabilities.
• Ability to distinguish robust technical fixes from superficial patches.
• Strong debugging and code-review skills.
• Ability to read AI-agent execution traces and diagnose failures.
• Strong analytical and adversarial problem-solving mindset.
• Comfortable working independently on technically complex tasks.

Preferred Skills:

• RLHF or AI evaluation experience.
• Benchmark or evaluation-environment authoring.
• AI coding-agent evaluation.
• Red teaming, AppSec, or penetration testing.
• CTF or security challenge experience.
• Linux and shell scripting.
• Experience with Node.js, Go, or Java.
• Experience creating test harnesses, graders, or automated verification systems.

Ideal Profiles:

• Software Engineers
• Security Engineers
• Application Security Engineers
• ML / AI Engineers
• AI Evaluation Engineers
• Benchmark Authors
• Red Team Engineers
• Penetration Testers
• Coding Agent / AI Agent Engineers

Skills

AI Evaluation, AI Security, AppSec, Application Security, Benchmark, CTF, Docker, Penetration Testing, Pentesting, Python, RED Teaming, RLHF, Securities Research, Security, Test Automation, Test Harness, Testing, Verifier, pytest