RL Environment Engineer Intern

Eigent; Greater London; Hybrid; GBP 18,000 - 24,000; Part time

Job summary

Eigent is seeking an RL Environment Data Engineer / Researcher Intern to help design and refine reinforcement learning training environments across domains in collaboration with researchers and engineers. You will assist with data collection, task definition, reward design, evaluation, and post-training checks.

This internship targets students or early-career researchers eager to gain hands-on experience with RL environments, data evaluation, and AI agents.

Qualifications

• Currently pursuing or recently completed a degree in Computer Science, AI, or related field.
• Good Python coding skills to build scripts and data pipelines.
• Comfortable using AI coding tools for rapid experimentation.
• Foundational understanding of RL, post-training, reward design, or data evaluation.
• Interest in turning real-world tasks into trainable RL environments.

Responsibilities

• Assist in designing and refining RL training environments across task domains.
• Help collect, clean, structure, and evaluate data for RL environments.
• Support task objectives, reward functions, and evaluation standards.
• Identify loopholes in reward design and test approaches to prevent reward hacking.
• Run experiments in validation environments and report findings.
• Collaborate with research, engineering, and data teams to improve coverage and reliability.
• Keep up with RL environment research and share relevant findings.

Skills

Python

Data pipelines

Experimentation

Reinforcement learning basics

Code generation tools

Education

Degree in Computer Science or AI

Tools

Pandas

Git

Job description

Eigent is seeking an RL Environment Data Engineer / Researcher Intern to help design and refine reinforcement learning training environments across domains in collaboration with researchers and engineers. You will assist with data collection, task definition, reward design, evaluation, and post-training checks.

This internship targets students or early-career researchers eager to gain hands-on experience with RL environments, data evaluation, and AI agents.