Drive AI security innovation as an Adversarial AI Systems Engineer, focused on hardening LLM-driven deployments against threats. Your role is essential for maintaining robust AI product safety.
In this hands-on technical position, you will identify vulnerabilities and test AI systems against adversarial attacks. You'll engage in prompt injection methods and develop new testing scenarios while documenting critical findings for future reference and collaboration.
Key Responsibilities:
• Implement adversarial testing strategies for AI systems
• Carry out simulations of various attack methods
• Design tools to aid in automated testing
• Evaluate model performance under adversarial conditions
• Provide comprehensive documentation of vulnerabilities
Requirements:
• Strong expertise in adversarial ML or AI security
• Experience with LLM systems like OpenAI
• Excellent Python programming capabilities
• Understanding of embedding pipelines and API deployments...