Senior AI Security Engineer

This position is posted by Jobgether on behalf of a partner company. We are currently looking for a Senior AI Security Engineer in United States.

This role offers a unique opportunity to work at the forefront of AI security, focusing on protecting next-generation autonomous systems from emerging threats. You will play a critical role in identifying vulnerabilities in agentic AI environments and designing innovative defenses against adversarial attacks. Operating in a highly technical and research-driven environment, you will bridge the gap between cutting-edge security concepts and real-world production systems. The position involves close collaboration with engineering teams to deploy scalable, high-performance security solutions. You will contribute to shaping how AI agents safely interact with untrusted data and external systems. This is a high-impact role where your work directly influences the resilience and trustworthiness of advanced AI technologies. The environment values experimentation, ownership, and continuous learning.

• Research and analyze emerging threats targeting AI agents, including prompt injection, context poisoning, and adversarial manipulation techniques.
• Design and implement secure, scalable workflows that govern interactions between AI agents and external systems such as web environments.
• Develop innovative detection and mitigation strategies to identify malicious inputs and unsafe contextual signals in AI-driven systems.
• Integrate security controls into agent runtimes, ensuring safe reasoning, decision-making, and execution when handling untrusted data.
• Collaborate with engineering teams to translate research findings into production-ready security features and frameworks.
• Conduct proactive threat modeling to anticipate evolving risks as AI systems become more autonomous and complex.
• Build and enhance defensive mechanisms to detect and neutralize sophisticated attacks embedded in web content and data streams.
• Continuously evaluate and improve system resilience, balancing performance, scalability, and security effectiveness.

Requirements:

• Bachelor’s degree in Computer Science or equivalent practical experience; advanced degrees (MSc or PhD) are a plus.
• 3+ years of experience in applied AI, with proven deployment of scalable AI systems in production environments.
• Strong programming expertise in Python and experience with cloud-native architectures, including Kubernetes and distributed systems.
• Solid background in cybersecurity, application security, or browser technologies.
• Deep understanding of prompt engineering and vulnerabilities specific to AI and agent-based systems.
• Experience exploring ambiguous problem spaces and developing innovative, research-driven solutions.
• Strong knowledge of data modeling, version control, and high-performance system design.
• Excellent collaboration and communication skills, with the ability to work across research and engineering teams.
• Bonus: Experience with orchestration frameworks (e.g., LangChain, AutoGen), real-time data pipelines, or web rendering technologies (DOM, accessibility tree).
• Mindset focused on building secure, auditable, and fault-tolerant systems.

Benefits:

• Competitive compensation package aligned with experience and expertise.
• Opportunity to work on cutting-edge AI security challenges with real-world impact.
• Collaborative, inclusive, and innovation-driven work environment.
• Strong career growth opportunities within a rapidly scaling organization.
• Access to advanced tools, technologies, and research-driven projects.
• Flexible work arrangements supporting productivity and work-life balance.
• Comprehensive health and wellness benefits.