AI Security Researcher

Summary: The AI Security Researcher combines application security fundamentals with AI red teaming and agentic consulting. This role involves conducting deep engineering-level security assessments, researching offensive AI/ML attack vectors, and collaborating with development teams to enhance security processes for enterpris...

Accelerate Your Career in Cybersecurity

Pentera is the market leader in AI-native Security Validation, equipping enterprises with the platform to proactively test their defenses against the latest cyber attacks. Pentera proves which exposures are truly exploitable across the entire attack surface and drives remediation workflows that reduce real risk. Anchored in real-attack validation, the Pentera platform powers the full Continuous Threat Exposure Management (CTEM) cycle, from exposure discovery through prioritization, validation, and mobilization. Thousands of security teams around the world trust Pentera to close their security gaps before threat actors can exploit them.

With over 350 team members and 1,300 customers in more than 60 countries, Pentera is a growing company supported by top investors such as Insight Partners, K1, and The Blackstone Group.

If you want to grow your skills, make an impact, and be part of an innovative team, Pentera is the place for you.

About the role:

We're looking for an AI Security Researcher with a strong AppSec foundation. At the core, this is a deeply technical application security role at an engineering level. You'll sit with development teams, get involved in their processes, understand how software is actually built, and bring a security perspective from the inside. You'll enhance traditional AppSec with agentic tools and security layers, working directly with enterprise customers on hands-on engagements. On top of that defensive foundation, you'll layer AI-specific offensive capabilities: researching and executing attacks against AI/ML systems.

This is a unique opportunity to combine strong AppSec fundamentals with cutting-edge AI red teaming and agentic consulting, with a clear growth path as a researcher.

Roles and Responsibilities:

• Conduct deep, engineering-level application security work: review architectures, assess code, and embed with development teams as a technical peer throughout the development lifecycle
• Lead AI-focused security assessments and red team engagements for enterprise customers, identifying vulnerabilities in AI/ML systems, agentic workflows, and LLM-based applications
• Enhance traditional AppSec processes with agentic tools and AI security layers
• Research and develop novel attack techniques targeting AI/ML systems, including prompt injection, model manipulation, and agentic framework exploits
• Translate offensive findings into actionable security recommendations for customers and internal teams
• Stay at the forefront of AI security: continuously research emerging attack surfaces and contribute to the growing body of AI threat knowledge
• Deep, hands-on application security experience at an engineering level: someone who sits with dev teams, understands development processes from the inside, and reviews code and architectures as a peer (Must)
• At least 1 year of dedicated, immersive work in AI security: research, experimentation, or offensive engagements targeting AI/ML systems (Must)
• Offensive security capabilities with a focus on AI-specific attack vectors (Must)
• Strong understanding of AI/ML technologies, including LLMs, agentic systems, and common AI application architectures
• Development skills: comfortable reading and writing code, building tools, and understanding codebases
• Excellent communication skills and comfort working directly with enterprise customers
• Fluent English

Nice to have:

• Published research or public talks on AI security topics
• Experience with traditional penetration testing or red teaming
• Background in building or deploying AI/ML systems from the development side

We are an equal opportunity employer and we are committed to building a diverse and talented workforce. We do not discriminate on the basis of race, sex, religion, colour, national origin, gender, gender identity, sexual orientation, age, marital status, veteran status, medical condition, disability, or any other class or characteristic protected by applicable law. We we