Human Data for Reinforcement Learning (Contract) - Remote

Overview

We're an innovative AI startup developing a comprehensive evaluation suite for training and testing autonomous LLM based agents. Our platform pushes the boundaries of AI capability assessment through challenging, real-world problem scenarios.

In Short

• Seeking experienced technical professionals for designing problems to test autonomous AI agents.
• Contract role involving creation of RL environments across various technical domains.
• Design original, challenging technical problems.
• Create realistic terminal-based scenarios for professional workflows.
• Develop comprehensive RL environments including specifications and grading systems.
• Tasks must span multiple difficulty levels and technical areas.
• Ensure originality and pass plagiarism checks.
• Work remotely with flexible hours.
• Compensation based on tasks submitted.
• Opportunity for long-term partnership as the platform scales.

Requirements

• Advanced degree in Data Science, Computer Science, or related field.
• 3+ years of experience in data science, systems administration, or DevOps.
• Strong programming skills in Python, Bash, SQL.
• Experience with Linux/Unix systems.
• Understanding of containerization and networking.

Benefits

• Shape the future of AI evaluation.
• Flexible remote work environment.
• Collaboration with cutting-edge AI research engineers.
• Potential for long-term partnership.