Overview

Position: AI Red-Teamer — Adversarial AI Testing (Advanced)

Type: Hourly Contract

Compensation: $54–$111/hour

Location: Remote

Duration: Full-time or part-time, flexible

About Crossing Hurdles

Crossing Hurdles is a recruitment firm. We refer top candidates to our partners working with the world’s leading AI research labs to help build and train cutting-edge AI models.

Key Responsibilities

• Red-team AI models and agents by crafting jailbreaks, prompt injections, misuse cases, and exploit scenarios
• Generate high-quality human data: annotate AI failures, classify vulnerabilities, and flag systemic risks
• Apply structured approaches using taxonomies, benchmarks, and playbooks to maintain consistency in testing
• Document findings comprehensively to produce reproducible reports, datasets, and attack cases
• Flexibly support multiple projects including LLM jailbreaks and socio-technical abuse testing across different customers

Required Qualifications

• Prior red-teaming experience, such as AI adversarial work, cybersecurity, or socio-technical probing OR a strong AI background that supports rapid learning
• Expertise in adversarial machine learning, including jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction
• Cybersecurity skills such as penetration testing, exploit development, reverse engineering
• Experience with socio-technical risk areas like harassment, disinformation, or abuse analysis
• Creative probing using psychology, acting, or writing to develop unconventional adversarial methods

Application process

• Upload resume
• AI interview based on your resume (15 min)