Red Team - Security Researcher III

F5 Networks, Inc.; Warszawa; Hybrid; PLN 180,000 - 360,000; Full time

Job summary

F5 Networks, Inc. is seeking a Red Team Researcher with an AI security focus to proactively assess and improve our security posture across global infrastructure, AI/ML deployments, and APIs.

You will lead objective-based engagements, develop adversarial techniques, and translate findings into actionable hardening measures while mentoring teams and contributing to the security community.

Qualifications

• 5-8+ years in offensive cybersecurity (Red Teaming, advanced pen testing, vulnerability research).
• Experience in AI/ML security testing and LLM security concepts (OWASP Top 10 for LLMs).
• Strong programming/scripting in Python, Go, C++, or Rust for tool development.

Responsibilities

• Lead complex Red Team operations targeting global infrastructure, products, and AI/ML deployments.
• Perform AI/LLM penetration testing: prompt injection, model inversion, data poisoning, AML evasion.
• Develop exploits, C2 tooling, and offensive AI-enabled tech to bypass security controls.
• Research vulnerabilities in traditional and AI pipelines (MLOps, vector databases, hosting platforms).
• Collaborate with Engineering/Blue Teams to drive architectural hardening and risk mitigation.
• Share findings via published research and conference talks; mentor internal teams.

Skills

Offensive security

AI/LLM security

Programming (Python, Go, C++, Rust)

Cloud security (AWS/Azure)

Adversarial ML frameworks

Tools

PyTorch

TensorFlow

Hugging Face

Job description

At F5, we strive to bring a better digital world to life. Our teams empower organizations across the globe to create, secure, and run applications that enhance how we experience our evolving digital world. We are passionate about cybersecurity, from protecting consumers from fraud to enabling companies to focus on innovation. Everything we do centers around people. That means we obsess over how to make the lives of our customers, and their customers, better. And it means we prioritize a diverse F5 community where each individual can thrive.

Position Overview

F5 is looking for Red Team Researcher (AI Security Focus) to proactively compromise and evaluate the security posture of our internet-facing traffic management, security platforms, and emerging AI/ML implementations. You will operate within the Office of the CISO as a highly specialized offensive security expert. Moving beyond traditional penetration testing, you will research, develop, and execute advanced adversary emulation campaigns with a specific focus on AI infrastructure, Large Language Models (LLMs), and mission-critical APIs.

Key Responsibilities

• Lead complex, objective-based Red Team operations targeting F5's global infrastructure, products, and AI/ML deployments.
• Conduct specialized AI/LLM penetration testing, including prompt injection, model inversion, data poisoning, and adversarial machine learning (AML) evasion techniques.
• Research and develop custom exploits, C2 infrastructure, and offensive tooling leveraging AI to bypass modern security controls (EDR, WAF, XDR).
• Perform deep-dive vulnerability research on both traditional enterprise environments and AI pipelines (MLOps, vector databases, model hosting platforms).
• Partner directly with Engineering and Blue Teams to translate offensive findings into actionable architectural improvements, moving beyond patching to fundamentally harden systems.
• Contribute to the broader security community through published research, zero-day disclosures, and presentations at top-tier security conferences (e.g., DEF CON, Black Hat).
• Mentor internal engineering and security teams on the mindset of an advanced threat actor, specifically regarding the evolving landscape of AI-driven attacks.

Required Qualifications

• 5-8+ years of hands-on experience in offensive cybersecurity (Red Teaming, Advanced Penetration Testing, Vulnerability Research).
• Demonstrated experience in AI/ML security testing, including a deep understanding of the OWASP Top 10 for LLMs and Adversarial ML frameworks (e.g., MITRE ATLAS).
• Strong programming/scripting proficiency (Python, Go, C++, or Rust) for custom tool development and exploit modification.
• Deep understanding of modern attacker tradecraft, including advanced persistence, evasion techniques, memory injection, and lateral movement in both on-premise and cloud (AWS/Azure) environments.
• Familiarity with AI frameworks and libraries (e.g., PyTorch, TensorFlow, Hugging Face) and how they are deployed in enterprise architecture.
• Ability to translate highly technical exploit chains and zero-day research into strategic risk assessments for executive leadership.

Preferred Qualifications

• Proven track record of published security research, CVEs, bug bounty successes, or conference talks—especially in the realm of AI security or novel exploitation techniques.
• Relevant offensive security certifications (e.g., OSCP, OSEP, CRTO, CRTE, OSWE) are highly desirable.
• Experience compromising major cloud environments, SaaS platforms, and MLOps pipelines.

The Job Description is intended to be a general representation of the responsibilities and requirements of the job. However, the description may not be all-inclusive, and responsibilities and requirements are subject to change.

Please note that F5 only contacts candidates through F5 email address (ending with @f5.com) or auto email notification from Workday (ending with f5.com or @myworkday.com).

Equal Employment Opportunity

It is the policy of F5 to provide equal employment opportunities to all employees and employment applicants without regard to unlawful considerations of race, religion, color, national origin, sex, sexual orientation, gender identity or expression, age, sensory, physical, or mental disability, marital status, veteran or military status, genetic information, or any other classification protected by applicable local, state, or federal laws. This policy applies to all aspects of employment, including, but not limited to, hiring, job assignment, compensation, promotion, benefits, training, discipline, and termination.

F5 offers a variety of reasonable accommodations for candidates. Requesting an accommodation is completely voluntary. F5 will assess the need for accommodations in the application process separately from those that may be needed to perform the job. Request by contacting [e-mail].

Hybrid: Employees within 30 commutable miles of an F5 office are required to work from the office a minimum of 30 business days per quarter.

Remote: Primarily work from designated home location but can come into an F5 office to work or travel to an offsite location as needed.

Together, we're building a better digital world. Founded in 1996, F5 is a global leader in application delivery and security. Our premier platform helps customers secure and deliver every app, API, and piece of infrastructure across all environments. Backed by over three decades of expertise and 553 patents, our solutions protect against threats while ensuring fast, reliable digital experiences. With over 6,400 employees, we serve more than 23,000 customers in over 170 countries. To continue this work, we need people like you—the best minds in the industry. We're committed to a unique, human-first culture that encourages authenticity, prioritizes diversity and inclusion, and fosters the growth and success of our employees.