🛠 Tech Stack

💼 About This Role

You'll research and defend against emerging security threats to autonomous AI agents, such as prompt poisoning and context manipulation. You'll design and implement scalable detection controls that protect agents interacting with untrusted web content. This role bridges cutting-edge AI security research with practical, production-ready defenses.

🎯 What You'll Do

• Research prompt injection and context poisoning attack vectors
• Design high-performance pipelines for secure agent-web interactions
• Develop detection mechanisms for adversarial behaviors in LLM agents
• Integrate security controls into production agentic runtimes

📋 Requirements

• 3+ years of applied AI experience in production
• Expert-level Python and Kubernetes proficiency
• BSc in Computer Science or equivalent experience
• Experience in cybersecurity or browser-related technologies

✨ Nice to Have

• Hands-on experience with LangChain or AutoGen
• Experience building real-time data pipelines for traffic analysis
• Understanding of DOM manipulation or Accessibility Tree

🎁 Benefits & Perks

• 🤝 Collaborative culture with open communication
• 💡 Opportunities to implement new ideas
• 🏆 Work with Fortune 500 clients
• 🌍 Global impact with top investors