Expert Talent Pool, Agents and Reinforcement Learning

Responsibilities

• Design reinforcement learning environments with Python and Docker setups
• Build robust verifiers and reward functions that resist agent gaming
• Translate business workflows in ERP, CRM, finance and operations into measurable scenarios
• Integrate tools and REST APIs and build test harnesses using pytest or similar
• Lead agent demonstration and computer-use programs, setting trace collection standards
• Grade and repair agent trajectories and mentor contributors on evaluation practices

Requirements

• At least 5 years in software engineering, QA automation, ML, RL or business systems
• Strong Python skills and experience building tools or services
• Experience designing environments, verifiers or test harnesses using pytest, Playwright, Selenium or Gymnasium
• Hands-on experience with agent or RL data such as demonstrations and trajectory grading
• Experience with REST APIs and Docker

Preferred Qualifications

• Experience leading or reviewing data, evaluation or demonstration work
• Expertise modeling workflows in Salesforce or ERP platforms
• Degree in computer science, engineering or a related field

Benefits

• Pay of $80 to $200 per hour based on hours worked, project, field and level
• Remote work on projects running from one week to several months