Logo-of-Tech-Collective-hiring-for-jobs-in-Denmark-on-GrabJobs

AI Red Team Specialist Lead Researcher in Agentic Security

icon briefcase Job Type : Full Time

Number of Applicants

 : 

000+

Click to reveal the number of candidates who applied for this job.
icon loader
Apply Now
icon loader Apply Now

Let AI Supercharge Your Job Hunt!

JobCopilot scans 500,000+ company career sites daily to find jobs for you

Never miss an opportunity Save hours by auto-filling applications forms Land more interviews with tailored applications
happy man
thunder iconActivate JobCopilot

Job Description - AI Red Team Specialist Lead Researcher in Agentic Security

Company Description

 

 

Job Description

We’re looking for an experienced red teamer with proven credentials in agentic red teaming to join our advanced product and research team. 

What you’ll do 

You’ll join the team dedicated to building and developing a tool that dynamically tests and evaluates large language models (LLMs) and their native application context for vulnerabilities. 

You’ll be working with seasoned reverse engineers, application pentesters, red teamers, and data scientists, bridging multiple digital disciplines by creating a unique suite that gives our clients the capability to test, remediate, and harden their agentic workloads.  

What you’ll bring  

Most of all, we value ingenuity, curiosity, and drive. You may be a great fit for this role if you have experience with: 

  • Building or contributing to tools used for dynamic application testing  
  • Working extensively with open source or proprietary tools used for web and application pentesting 
  • Actively adopting LLMs and Model Context Protocol (MCP) in automating and enhancing your penetration tests 
  • Spending time researching agentic vulnerabilities and attending relevant trainings or conferences  

To fit right in here at The Tech Collective: 

  • You should be genuinely curious about new developments within the red teaming domain 
  • You possess the willingness to tackle new and technical challenges as they arise 
  • You know how to break down and structure complex assignments and enjoy sharing your knowledge and insights with your team members  
  • You possess a startup mentality to help drive the innovation and ingenuity of our red team products 
  • You can cooperate seamlessly with different profiles in a highly diverse team of researchers, developers, consultants, and red teamers 

We don’t expect you to know everything – after all, agentic security is a rapidly evolving field! In this role, we’re looking for someone who wants to own, develop, and innovate the product modules related to testing the application context (e.g., API security, cryptographic implementation, broken authentication, RBAC) and supporting infrastructure (e.g., misconfigurations, server-side vulnerabilities) for the agents that we test. 

To succeed in this role, your experience and competencies should include: 

Professional experience 

  • A minimum of five years’ progressive experience in enterprise red teaming or offensive research 
  • A proven track record of web application pentesting with an emphasis on remediation and hardening 
  • Experience defining and driving product roadmaps for red team tools (not required, but highly valued) 
  • Demonstrated ability to evaluate complex technology stacks, including common cloud platforms (M365/Azure, Google, or AWS), CI/CD pipelines, and AI-powered platforms and systems 
  • Experience communicating technical findings to non-technical stakeholders and the ability to bring technical assessments to life 

Technical competencies 

  • Familiarity with both Mitre and OWASP frameworks, and experience applying them in client reporting 
  • Relevant security certifications (e.g., OSCP, OSCE, OSEP, GIAC GPEN/GXPN, etc.) are a plus, indicating solid foundational knowledge and commitment to the offensive security field. 
  • Prior experience developing agent-specific attack types such as prompt injection, memory & context poisoning, or jailbreaking 
  • A working understanding of MCP, LLM pipelines, the functional aspects of LLMs, and how modern agent solutions are integrated with widely used cloud suites such as M365 or AWS  

Finally, experience in intermediate to advanced vulnerability research related to applications or operating systems will be considered a strong plus, but is not a requirement for this role. 

What we offer 

On top of a competitive salary and bonus package, we offer you the opportunity to join a unique team of experts and enthusiasts in your field. Our expectations are matched by our willingness to invest in your development – whether through training, conferences, or the opportunity to pursue research in areas you’re passionate about. 

We combine remote work with meaningful co-working at our offices in Copenhagen and will provide you with the tooling and hardware required to reach our goal of building a unique red team platform. 

For questions or enquiries, feel free to contact Anders Rømer Skøtt at [email protected] // +45 31717487. 

Original job AI Red Team Specialist Lead Researcher in Agentic Security posted on GrabJobs ©. To flag any issues with this job please use the Report Job button on GrabJobs.
Apply Now
Share Job
Share Job

About the Company

Tech Collective

Company Description

Read more about the company

Auto-Apply to AI Red Team Specialist Lead Researcher Jobs with your AI JobCopilot

thunder icon Auto-Apply with AI

Similar AI Red Team Specialist Lead Researcher Jobs in Denmark

GrabJobs is the no1 job portal in Denmark, connecting you to thousands of jobs fast! Find the best jobs in Denmark, apply in 1 click and get a job today!

Mobile Apps

Copyright © 2026 Grabjobs Pte.Ltd. All Rights Reserved.