Remote LLM Safety & Red Teaming Expert

Weekday 1; United States; Remote; USD 69,000 - 124,000; Part time

Job summary

Weekday 1 is seeking an experienced AI Safety & Red Teaming Specialist for a remote contract. You will assess adversarial AI risks, design evaluation methodologies, and improve the robustness of large language models against real-world threats.

This role emphasizes ethical hacking, rigorous testing, and transparent reporting. Collaborate with cross-functional teams to translate security findings into concrete recommendations, develop regression test suites, and document testing approaches for

Qualifications

• 2+ years of experience in AI Safety, Adversarial ML, or related field.
• Hands-on experience researching prompts, jailbreaks, adversarial attacks, or tool-use.
• Strong understanding of modern LLM architectures and safety evaluation methodologies.
• Experience developing security assessments, regression testing, and adversarial evaluation strategies.
• Excellent analytical and communication skills; ability to explain complex findings clearly.
• Ability to collaborate within cross-functional teams.

Responsibilities

• Design and implement advanced evaluation methodologies for AI system safety, including ethical jailbreak testing, prompt injection detection, LLM red teaming, and tool-use abuse scenarios.
• Develop cross-domain adversarial testing strategies to uncover complex, multi-turn attack patterns and model vulnerabilities.
• Build, maintain, and enhance regression test suites to continuously assess jailbreak susceptibility and prompt injection risks.
• Create comprehensive evaluation frameworks that simulate real-world adversarial threats to improve AI robustness and reliability.
• Collaborate with technical teams to translate security findings into actionable recommendations for AI safety improvements.
• Document testing methodologies, findings, and best practices through clear technical reports and presentations for both technical and non-technical stakeholders.

Skills

AI Safety

LLM Red Teaming

Prompt Injection

Adversarial Machine Learning

Education

Master's or PhD in CS/Cybersecurity/ML/AI

Job description

Weekday 1 is seeking an experienced AI Safety & Red Teaming Specialist for a remote contract. You will assess adversarial AI risks, design evaluation methodologies, and improve the robustness of large language models against real-world threats.

This role emphasizes ethical hacking, rigorous testing, and transparent reporting. Collaborate with cross-functional teams to translate security findings into concrete recommendations, develop regression test suites, and document testing approaches for