Unknown Company

Offensive Cybersecurity Engineer for AI Evaluation

SEATAC, Washington • Posted Today
Remote Contract technology

Role Overview

Build and strengthen reinforcement learning environments that evaluate frontier AI systems in offensive cybersecurity scenarios. This long-term, remote engagement contributes to research on advanced security risks in emerging technologies through rigorous, iterative benchmark development.

Key Responsibilities

  • Design and implement complex offensive cybersecurity reinforcement learning environments.
  • Harden existing benchmarks against advanced AI interactions.
  • Develop rigorous evaluation criteria for frontier AI models.
  • Collaborate on an ongoing basis to refine security scenarios as vulnerabilities evolve.

Qualifications

  • Professional experience in offensive cybersecurity or penetration testing.
  • Strong background building or hardening technical environments.
  • Experience developing security benchmarks or secure environments is valuable.
  • Familiarity with reinforcement learning or AI evaluation frameworks is preferred but not required.
  • Interest in AI safety and model evaluation.
  • Comfort working independently on a long-term, hourly remote engagement.

Work Terms

  • Fully remote independent contractor engagement.
  • Work may be completed on your own schedule.
  • No access to confidential or proprietary information from any employer, client, or institution is required.

Compensation

  • $150 per hour.
  • Payments are issued weekly based on services rendered.

Eligibility

  • H-1B and STEM OPT candidates are not eligible at this time.

Offensive Cybersecurity Engineer for AI Evaluation in SEATAC at Unknown Company

This position is listed as contract and able to be worked remotely.

Back to Job Search