This job has expired
This position was posted on March 28, 2026 and is likely no longer accepting applications. We've kept it here for historical reference. Check out the similar jobs below!
Job Overview
Location
US - Distributed
Job Type
Full-time
Category
Software Engineering
Date Posted
March 28, 2026
Full Job Description
đź“‹ Description
- • As a Senior AI Security Engineer at Menlo Security, you will play a critical role in safeguarding the next generation of autonomous AI agents by researching and defending against emerging threats like prompt poisoning, context manipulation, and adversarial behaviors in LLM-powered systems. Your work will directly contribute to securing AI agents that operate in real-world, untrusted environments, ensuring they can reason and act safely without compromising performance or integrity.
- • You will research emerging agentic threats such as prompt injection, context poisoning, adversarial content embedding, and misuse of agent planning and reasoning mechanisms, translating findings into actionable security insights.
- • You will architect scalable, high-performance agentic workflows that secure interactions between AI agents and external web content, focusing on resilience and efficiency.
- • You will develop novel detection and mitigation techniques for identifying malicious prompts, unsafe contextual signals, and adversarial behaviors in LLM-powered agents, prototyping solutions for real-world deployment.
- • You will implement these security controls within agentic runtimes, enabling agents to safely reason over and act on external data sources while maintaining operational integrity.
- • You will collaborate closely with applied engineering teams to integrate research-driven security mechanisms into production systems, balancing security effectiveness with agent performance and latency.
- • You will engage in proactive threat modeling to anticipate evolving risks as agent capabilities and autonomy increase, ensuring long-term resilience against future attack vectors.
- • You will build defensive mechanisms within the browser surrogate to detect and neutralize complex context poisoning and injection attempts embedded in untrusted web content, leveraging Menlo’s isolation technology.
- • You will join a mission-driven, well-funded company trusted by Fortune 500 enterprises, top global banks, and the U.S. Department of Defense, where your work protects some of the most sensitive digital interactions in the world.
- • You will be part of a collaborative, inclusive, and innovative culture rooted in Menlo’s five core values: Stay Aligned, Get It Done, Customer Empathy, Think Creatively, and Help Each Other Out — empowering you to take initiative and shape the future of AI security.
🎯 Requirements
- • BSc in Computer Science or equivalent experience in high-scale cloud engineering; MSc or PhD in a relevant field 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; direct experience with agentic AI systems in production is a significant advantage.
- • Expert-level Python proficiency, deep experience with Kubernetes and cloud-native orchestration, and strong skills in advanced data modeling and version control (e.g., Git).
🏖️ Benefits
- • Opportunity to work on cutting-edge AI security challenges at the forefront of protecting autonomous agents in real-world, adversarial environments.
- • Collaborative, inclusive, and innovative company culture with strong emphasis on open communication, initiative-taking, and shared purpose.
- • Backed by top-tier investors including Vista Equity Partners, General Catalyst, JPMC, American Express, HSBC, and Ericsson Ventures, ensuring stability and resources for impactful work.
Skills & Technologies
About Menlo Security Inc.
Menlo Security Inc. offers a cloud-based security platform designed to protect organizations from malware and phishing threats. Their core technology, the Cloud Secure Gateway, isolates potentially harmful content in a virtual environment, preventing it from reaching end-user devices. This approach eliminates threats at the source, ensuring a safe browsing experience for users across all devices and locations. The platform integrates with existing security infrastructure and provides comprehensive visibility and control over web, email, and document-based threats. Menlo Security's solution is built on a Zero Trust principle, focusing on containment and adaptive security to defend against evolving cyberattacks and protect sensitive data.
Subscribe to the weekly newsletter for similar remote roles and curated hiring updates.
Newsletter
Weekly remote jobs and featured talent.
No spam. Only curated remote roles and product updates. You can unsubscribe anytime.
