Senior AI Security Engineer - Pioneering Agentic AI Defense
Join Menlo Security, a leader in cybersecurity, as we tackle the next frontier of digital defense: securing autonomous AI agents. Trusted by Fortune 500 companies, 9 of the top 10 global banks, and the Department of Defense, our mission is to enable secure connection, communication, and collaboration without compromise.
The world has fundamentally shifted, and so has the threat landscape. As AI agents become increasingly autonomous and integrated, new vulnerabilities emerge. With robust funding from top-tier investors like Vista Equity Partners, General Catalyst, JPMC, American Express, HSBC, and Ericsson Ventures, and a rapidly growing team, we're building the future of secure AI.
We're looking for a passionate, ethical, and agile Senior AI Security Engineer to spearhead the research, design, and implementation of novel techniques to detect and mitigate adversarial threats against agentic AI systems. If you're ready to define the security standards for the AI-driven future, this is your chance.
What You'll Do (Core Responsibilities)
Innovate & Research Emerging Threats: Lead investigations into cutting-edge 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 critical agent-to-web interactions.
Develop Next-Gen Detection & Mitigation: Prototype and deploy novel techniques for identifying malicious prompts, unsafe contextual signals, and adversarial behaviors in LLM-powered agents.
Integrate Agent Security Controls: Embed these advanced security controls directly within agentic runtimes, ensuring agents can safely reason over and act on external, potentially untrusted, data sources.
Collaborate & Deliver: Work closely with applied engineering teams to translate your research into practical, production-ready security mechanisms, balancing effectiveness with agent performance.
Proactive Threat Modeling: Continuously analyze the evolving AI threat landscape, anticipate future risks as agent capabilities and autonomy increase, and proactively develop countermeasures.
Strengthen Adversarial Resilience: Engineer defensive mechanisms within our browser surrogate to detect and neutralize complex context poisoning and injection attempts embedded in web content.
What You'll Bring (Qualifications)
BSc in Computer Science or significant practical experience in high-scale cloud engineering. A relevant MSc or PhD is a strong advantage.
3+ years of hands-on experience in applied AI, with a proven track record of deploying high-scale AI systems in production environments. Experience with agentic systems in production is a significant plus.
Expert-level proficiency in Python, coupled with deep experience in Kubernetes (k8s) and cloud-native orchestration.
Strong understanding of advanced data modeling and meticulous version control practices.
Significant experience in cybersecurity or browser-related technologies is highly preferred.
Deep understanding of prompt engineering techniques and their potential exploitation in agentic systems.
A curious mindset with the ability to navigate ambiguous problem spaces, experiment with new ideas, and iteratively develop effective security solutions.
Bonus Points For (Nice to Have)
Hands-on experience with AI 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 web page rendering, how to programmatically manipulate the DOM, or Accessibility Tree for security enhancement.
A "security-first" mindset, with a proven bias toward building auditable, traceable, and fault-tolerant systems.
Why Menlo Security?
Our culture is the engine of our success: collaborative, inclusive, and fun! We live by our five core values: Stay Aligned, Get It Done, Customer Empathy, Think Creatively, and Help Each Other Out. We believe in open communication, championing new ideas, and sharing a mutual commitment to our collective goals. Here, you'll find tremendous opportunities to take initiative, implement groundbreaking ideas, and contribute to building a lasting legacy in the cybersecurity space.
Menlo Security is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, sex, color, religion, sexual orientation, gender identity, national origin, protected veteran status, or on the basis of disability.