- Work from
- Worldwide
- Contract
- Full-time
- Salary
- $35 – $70 / hour
- Posted
- 16 November 2026
- Apply by
- 15 January 2027
You will help build practice environments and evaluate agent behavior, supporting the development of AI systems that interact with software and workflows.
About the role
Join a paid talent pool supporting projects in AI agents and reinforcement learning.
Responsibilities
- Build reinforcement learning environments in Python and Docker where agents can take actions and receive feedback.
- Turn business workflows, such as ERP processes, CRM updates, and spreadsheet operations, into trainable scenarios.
- Write tasks, connect tools and REST APIs, and create systems to verify agent actions.
- Create and grade agent demonstrations, including screen recordings of task execution.
- Collect execution traces, evaluate agent trajectories, and investigate failures.
Requirements
- Zero to five years of experience in software engineering, QA automation, machine learning or reinforcement learning engineering, operations analysis, or substantial use of business software.
- Experience writing Python or building automations or reports in Excel, Salesforce, or an ERP system.
- Experience testing, scripting, or automating multi-step software tasks, such as test cases, API calls, or UI steps.
- Familiarity with Docker, REST APIs, or Gymnasium and OpenAI Gym-style environments is useful.
- Experience with pytest, Playwright, or Selenium, or documenting business workflows and screen-based tasks, is useful.
- Strong software fundamentals or hands-on knowledge of business workflows; prior AI data experience is not required.
Salary
Compensation is $35 to $70 per hour, depending on the project, field, and experience. Compensation Range: $72.8K - $145.6K
Compensation & Benefits
Payment is based on hours worked.
Location
Remote. Projects typically last from one week to several months.
M
A
N
P
C
Discussion
No comments yet. Ask a question or share a tip about this role.