Job Information
Menlo Security, Inc. Senior AI Security Engineer in Mountain View, California
Core Responsibilities
- Research Emerging Agentic Threats:Investigate new attack vectors against AI agents, including prompt injection, context poisoning, adversarial content embedding, and misuse of agent planning and reasoning mechanisms.
- Architect Scalable Agentic Workflows:Design and implement robust, high-performance pipelines that secure agent-to-web interactions.
- Develop Novel Detection and Mitigation Techniques:Design and prototype new approaches for identifying malicious prompts, unsafe contextual signals, and adversarial behaviors in LLM-powered agents.
- Agent Security Controls:Implement these techniques as security controls within agentic runtimes, ensuring agents can safely reason over and act on external data sources.
- Collaborative Engineering:Partner closely with applied engineers to integrate research-driven security mechanisms into production systems, balancing security effectiveness with agent performance.
- Proactive Threat Modeling:Continuously evaluate the evolving AI threat landscape and anticipate future risks as agent capabilities and autonomy increase.
- Adversarial Resilience:Build defensive mechanisms within the browser surrogate to detect and neutralize complex context poisoning and injection attempts embedded in web content.
Qualifications
BSc in Computer Science or significant experience in high-scale cloud engineering; a relevant MSc or PhD is a strong advantage.
3+ years of experience in applied AI, with a proven track record of deploying high scale AI systems in production environments. Agentic experience in production environments is an important advantage.
Expert-level Python; deep experience with k8s and cloud-native orchestration; proficiency with advanced data modeling and version control.
Significant experience in cybersecurity or browser-related technologies is highly preferred.
Deep understanding of prompt engineering techniques and how they can be exploited in agentic systems.
Ability to explore ambiguous problem spaces, experiment with new ideas, and iterate toward effective security solutions.
Nice to Have
Hands-on experience with orchestration frameworks (e.g., LangChain, AutoGen) and / or standardized communication protocols like MCP.
Experience building immutable event streams and high-speed data pipelines for real-time traffic analysis.
Understanding of how web pages are rendered and how to programmatically manipulate the DOM or Accessibility Tree to enhance security.
A "security-first" mindset with a bias toward building auditable, traceable, and fault-tolerant systems.