Remote RL Scenario Designer | Build & Test Sim Environments

Openkrill; United States; Remote; USD 102,000 - 146,000; Full time

Job summary

Terac is recruiting AI researchers and machine learning engineers to participate in building reinforcement learning environments for our remote platform. You will design and test agent scenarios, configure environmental parameters, and document your workflow for usability improvements.

Candidates should have hands-on experience in RL or simulation, and be comfortable working remotely. Compensation is $90 per hour, with participation in a study-focused program connecting researchers with AI teams.

Qualifications

• Hands-on experience in machine learning or artificial intelligence research.
• Background building simulations or reinforcement learning environments.
• Familiarity with configuring platform interfaces and defining reward structures.

Responsibilities

• Design and build specific scenarios within a remote reinforcement learning platform
• Configure environmental parameters and define agent interaction rules
• Test initial agent behaviors to validate your scenario structure
• Walk us through your workflow and highlight areas for platform improvement

Skills

Reinforcement learning

Simulation design

Platform configuration

Tools

RL platforms

Job description

Terac is recruiting AI researchers and machine learning engineers to participate in building reinforcement learning environments for our remote platform. You will design and test agent scenarios, configure environmental parameters, and document your workflow for usability improvements.

Candidates should have hands-on experience in RL or simulation, and be comfortable working remotely. Compensation is $90 per hour, with participation in a study-focused program connecting researchers with AI teams.