Zoom

Requirements

• Lead the offensive verification of AI systems and pipelines
• Design and execute deep, unconstrained assessments of AI models, pipelines, and agents
• Identify where AI security, safety, or privacy controls fail under pressure
• Evaluate data, training, and deployment pipelines for risks like model poisoning, prompt injection, or fine-tuning abuse
• Research, prototype, and operationalize machine learning–driven approaches to automatically detect, predict, and mitigate AI-related risks

Benefits

• 401k Matching
• Certification Support
• Flexible Hours
• Gym Membership
• Health Insurance
• Home Office Budget
• Learning Budget
• Paid Time Off

Skills

Requirements

• Developing an Assessment Methodology and Strategy
• Designing an Evaluation Framework
• Identifying Systemic Risks
• Designing Risk Evaluation Protocols
• Providing Strategic Technical Guidance
• Integrating Advanced Evaluation Techniques
• Creating a scalable evaluation infrastructure
• Ensuring engineering excellence and technical guidance

Benefits

• 401k Matching
• Certification Support
• Flexible Hours
• Gym Membership
• Health Insurance
• Home Office Budget
• Learning Budget
• Paid Time Off

Skills