Job Details

We're looking for a Research Engineer focused on building and evaluating training environments for AI agents. This role sits at the intersection of reinforcement learning, agent evaluation, and applied ML research, with a strong emphasis on understanding agent behavior, failure modes, and scalable environment design.

You'll work on creating benchmark tasks, analyzing agent rollouts, validating environment quality, and developing repeatable workflows for training and evaluation. The ideal candidate has strong ML fundamentals, is highly analytical, and enjoys both experimentation and hands-on engineering.

Requirements:

• Strong background in machine learning through industry experience or advanced studies in CS/ML
• Familiarity with RL concepts, agent systems, or training/evaluation pipelines
• Ability to design experiments, analyze model behavior, and identify patterns in failures
• Experience building scalable workflows, automation, or data pipelines

Nice to have:

• Hands-on RL or agent training experience
• Benchmarking, evaluation, or dataset curation experience
• Exposure to AI robustness, adversarial testing, or safety evaluations
• Research publications or open-source contributions in ML/AI systems

Note: Even if you do not have the set experience but can showcase some form of brilliance in terms of a project, educational background or work experience then feel free to apply either way. There is always a position for someone extraordinary.

Interview process is three steps:

Intro Call

Technical Round

On-site