Generative AI Associate – Red Teaming Specialist( Dutch Language )

We are seeking a self-motivated and clever Red Teaming Specialist to join our global subject matter expert team. This role is strictly "in-country" for candidates currently residing in the

Netherlands

. You will be on the frontlines of AI security, crafting adversarial prompts to bypass LLM guardrails and working with data scientists to secure the next generation of AI.

Key Responsibilities

* Adversarial Prompting: Craft "sneaky" prompts to bypass filters and guardrails, specifically targeting vulnerabilities in Dutch and English models.

* Deep Training: Complete onboarding in AI/ML, jailbreaking, and specific project security guidelines.

* Collaborative Security: Assist data scientists with automated model attacks and work with QA leads to refine safety protocols.

* Evolving Defense: Stay current on LLM capabilities to evolve team methods as new threats emerge.

* Productivity Goals: Maintain high handling speeds and meeting prompt-volume targets without sacrificing quality.

What We Need You to Bring

* Bilingual Expertise: Superior writing skills in both Dutch and English. You must know when to strictly follow linguistic rules and when to break them to test AI responses.

* Adversarial Mindset: Creative, "out-of-the-box" thinking with sharp attention to detail.

* Resilience & Grace: The ability to navigate shifting guidelines and project ambiguity with a proactive attitude.

* Remote Discipline: Self-motivated enough to thrive in a distributed team environment.

* ZipRecruiter

What We Offer (Netherlands Compliance)

* Transparency: Honest, direct feedback and clear career progression milestones.

Our Selection Flow

1. Technical Challenge: Access our Adversarial AI Assessment to demonstrate your prompting creativity.

2. Debrief Call: Immediately following the assessment, we will schedule a call to discuss your methodology and our operational roadmap.