RL Environment Architect & Data Research Engineer

Eigent AI; Greater London; Hybrid; GBP 65,000 - 85,000; Full time

Job summary

Eigent AI is seeking an RL Environment Data Engineer / Researcher to design and refine reinforcement learning training environments. This role emphasizes data collection, task definition, and the implementation of anti-reward-hacking mechanisms.

The ideal candidate will have strong Python coding skills and a solid understanding of reinforcement learning. Responsibilities include collaborating with multiple teams to improve RL tasks and validation environments.

Qualifications

• Strong coding skills in Python to build data pipelines and evaluation tools.
• Understanding reinforcement learning and environment design.
• Experience in data quality assessment preferred.

Responsibilities

• Design and improve RL training environments.
• Collect, clean, structure, and evaluate data for RL models.
• Define task objectives and reward functions.

Skills

Python programming

Reinforcement Learning

Data evaluation

Data scraping

Job description

Eigent AI is seeking an RL Environment Data Engineer / Researcher to design and refine reinforcement learning training environments. This role emphasizes data collection, task definition, and the implementation of anti-reward-hacking mechanisms.

The ideal candidate will have strong Python coding skills and a solid understanding of reinforcement learning. Responsibilities include collaborating with multiple teams to improve RL tasks and validation environments.