Offensive Cybersecurity Engineer – RL Environments for AI Evaluation

This is a fully remote position, open to applicants in United States.

📋 Description

• Create and develop environments for offensive cybersecurity using reinforcement learning techniques.

• Strengthen current benchmarks to endure sophisticated AI interactions.

• Formulate detailed evaluation standards for cutting-edge AI models.

• Work collaboratively on a long-term hourly basis to refine security scenarios.

• Consistently enhance and secure environments for thorough evaluations of AI systems.

⛳️ Requirements

• Proven experience in offensive cybersecurity or penetration testing.

• Solid technical expertise in constructing or fortifying secure technical environments.

• Ability to engage in long-term hourly remote projects comfortably.

• A keen interest in AI safety and model assessment.

• Knowledge of reinforcement learning or AI evaluation frameworks is appreciated, though not mandatory.

🏝️ Benefits

• Compensated project.

• Hourly pay rate of $150.

• Opportunity for long-term remote work.