Enterprise AI Agent Evaluation Infrastructure Engineer

MaxIT Consulting - Max Corporate Group; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

MaxIT Consulting - Max Corporate Group in San Francisco, CA is seeking an Agent Evaluation Infrastructure Engineer to design and build the environments, evaluation systems, and supporting infrastructure used to train and assess long-horizon enterprise AI agents.

You will tackle engineering and research problems behind realistic agent environments, post-training systems, and reliable evaluation of multi-step workflows, with production-quality focus.

Qualifications

• Hands-on experience with AI environments and evaluations.
• Reinforcement learning infrastructure experience.
• Strong software engineering fundamentals.
• Ability to build and ship technical infrastructure.
• Understanding of evaluation methodology, reward design, graders, and agent trajectories.
• Ability to work across languages and technology 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

RL infrastructure

Software engineering

Evaluation design

Agent trajectories

Tools

Grader pipelines

Job description

MaxIT Consulting - Max Corporate Group in San Francisco, CA is seeking an Agent Evaluation Infrastructure Engineer to design and build the environments, evaluation systems, and supporting infrastructure used to train and assess long-horizon enterprise AI agents.

You will tackle engineering and research problems behind realistic agent environments, post-training systems, and reliable evaluation of multi-step workflows, with production-quality focus.