Remote AI Safety & Red Teaming Expert

Weekday AI (YC W21); United States; On-site; USD 68,880 - 123,984; Part time

Job summary

Weekday AI (YC W21) is hiring an AI Safety & Red Teaming Specialist to enhance the security of next-gen AI systems. This remote role requires expertise in adversarial AI and LLM safety methodologies to identify vulnerabilities and develop robust evaluation frameworks.

The ideal candidate has a passion for AI security and a strong background in ethical hacking, contributing to AI safety tools and research. Join a team dedicated to improving AI resilience against real-world threats.

Qualifications

• 2+ years of experience in AI safety, adversarial machine learning, or related field.
• Experience with prompt injection, ethical jailbreaks, or adversarial attacks.
• Strong understanding of modern LLM architectures and AI safety methodologies.

Responsibilities

• Design advanced evaluation methodologies for AI system safety.
• Develop adversarial testing strategies for uncovering attack patterns.
• Collaborate with teams to provide actionable AI safety recommendations.

Skills

AI Safety

LLM Red Teaming

Prompt Injection

Adversarial Machine Learning

Education

Master's or PhD in Computer Science, Cybersecurity, Machine Learning, AI

Job description

Weekday AI (YC W21) is hiring an AI Safety & Red Teaming Specialist to enhance the security of next-gen AI systems. This remote role requires expertise in adversarial AI and LLM safety methodologies to identify vulnerabilities and develop robust evaluation frameworks.

The ideal candidate has a passion for AI security and a strong background in ethical hacking, contributing to AI safety tools and research. Join a team dedicated to improving AI resilience against real-world threats.