✨ The Role in One Sentence

Lakera is seeking an AI Security Researcher to discover vulnerabilities in AI systems and shape the future of AI security.

📋 What You'll Likely Do

• 30%: Discover and weaponize vulnerabilities in agentic systems using Lakera's security foundation models.

• 30%: Lead red-teaming operations against internal and customer AI stacks to identify LLM failures.

• 40%: Develop AI-native security benchmarks and contribute to practical evaluation standards for LLM defenses.

🧑‍💻 Profiles Doing This Job

• High Priority: Hands-on experience in offensive security, red teaming, penetration testing, or vulnerability research.

• High Priority: Strong engineering skills and ability to build custom tools and infrastructure.

• High Priority: Familiarity with modern machine learning systems or the ability to learn quickly.

📈 How This Role Will Look on Your CV

• Led security research to discover and mitigate vulnerabilities in AI systems.