Senior AI Security Engineer

📋 Description

• Research emergent agentic threats: prompts, context poisoning, and adversarial content.
• Architect scalable agentic workflows securing agent-to-web interactions.
• Develop detection and mitigation for malicious prompts and adversarial behavior in LLM agents.
• Implement security controls in agent runtimes for safe reasoning over external data.
• Collaborate with engineering to deploy security mechanisms in production systems.
• Proactive threat modeling to anticipate AI risks as autonomy grows.

🎯 Requirements

• BSc in CS or significant high-scale cloud engineering exp; MSc/PhD a plus.
• 3+ years applied AI with production deployments; agentic exp is a plus.
• Expert Python; deep Kubernetes and cloud-native orchestration; data modeling.
• Cybersecurity or browser tech exp highly preferred.
• Deep understanding of prompt engineering techniques.
• Ability to explore ambiguous problem spaces and iterate.

🎁 Benefits

• Collaborative culture with a growth mindset.
• Open communication and feedback culture.
• Five core values guiding work: Stay Aligned, Get It Done, Customer Empathy, Think Creatively, Help Each Other Out.
• Opportunity to influence security for autonomous AI at scale.