Research Engineer: RL Environments & Evaluation Systems

MaxIT Consulting - Max Corporate Group; San Francisco (CA); On-site; USD 170,000 - 250,000; Full time

Job summary

MaxIT Consulting - Max Corporate Group in San Francisco seeks a Research Engineer to build agent environments, evaluation systems, and infrastructure used to train and assess long-horizon enterprise AI agents.

You will design evaluation environments, define tasks and rewards, and develop production-grade infrastructure for rollouts and trajectory inspection, focusing on reliability and scalability in real-world enterprise settings.

Qualifications

• Hands-on experience with AI environments, evaluations, or RL infrastructure.
• Strong software engineering fundamentals.
• Ability to build and ship technical infrastructure.
• Understanding of evaluation methodology and reward design.
• Ability to work across languages and stacks.

Responsibilities

• Design evaluation environments for long-horizon enterprise agent workflows.
• Define tasks, state, tools, graders, and reward signals used to evaluate and improve agents.
• Build high-fidelity representations of complex enterprise software environments.
• Develop infrastructure for rollouts, orchestration, trajectory inspection, and grader pipelines.
• Measure both correctness and efficiency across multi-step agent behavior.
• Investigate evaluation failures, reward-quality issues, and agent behavior.
• Build production-quality systems rather than notebook-only research prototypes.

Skills

AI environments

Reinforcement learning infrastructure

Software engineering fundamentals

Technical infrastructure

Reward design

Graders

Agent trajectories

Polyglot programming

Job description

MaxIT Consulting - Max Corporate Group in San Francisco seeks a Research Engineer to build agent environments, evaluation systems, and infrastructure used to train and assess long-horizon enterprise AI agents.

You will design evaluation environments, define tasks and rewards, and develop production-grade infrastructure for rollouts and trajectory inspection, focusing on reliability and scalability in real-world enterprise settings.