Contractor Technical Reviewer - RL Environment Benchmarking

Mercor is hiring a Technical Reviewer to evaluate and refine benchmarking pipelines for reinforcement learning (RL) environments and agentic AI systems.

Responsibilities:

• Review RL environments and evaluate terminal conditions.
• Assess benchmarking pipelines for fairness and reproducibility.
• Provide technical feedback on code and documentation.
• Collaborate with researchers to refine evaluation metrics.
• Validate results across different runs and hardware setups.
• Document findings and recommend improvements.

Qualifications:

• Background in reinforcement learning, computer science, or applied AI research.
• Experience with RL environments.
• Understanding of benchmarking methodologies and evaluation metrics for RL tasks.
• Comfortable reviewing codebases in Python (PyTorch/TensorFlow a plus).
• Strong critical thinking skills.
• Detail-oriented.

Benefits:

• Influence the reliability of benchmarking in agentic AI research.
• Work on cutting-edge RL environments.
• Help establish standards for evaluation and reproducibility.
• Collaborate with researchers shaping the future of agentic AI systems.

Pay & Work Structure:

• Full-time hourly contractor to Mercor.
• Paid weekly via Stripe Connect.
• 40 hours/week commitment with flexible scheduling.
• Remote and flexible working style.

What is the last date for applying to the job?

Which countries are accepted for this remote job?