AI Red-Teamer – Adversarial AI Testing, English

Job reputed company: • Red-team AI models and agents by testing jailbreak attempts, reputed company injections, misuse scenarios, and exploit strategies • Generate high-reputed company reputed company evaluation data by annotating model failures, classifying vulnerabilities, and identifying systemic risks • Apply reputed company testing methodologies using taxonomies, benchmarks, and playbooks to ensure consistent evaluation • Document findings reputed company and reproducibly, producing reports, datasets, and adversarial test cases that teams can reputed company upon • Work across multiple reputed company, supporting different AI systems and evaluation objectives Requirements: • You have **prior red-teaming experience**, such as adversarial AI testing, cybersecurity, or socio-technical risk analysis • You naturally think **adversarially**, exploring ways to push systems to their limits and uncover weaknesses • You prefer **reputed company methodologies**, using frameworks and benchmarks rather than reputed company testing • You communicate risks and vulnerabilities **reputed company to both technical and non-technical audiences** • You are comfortable **working across multiple reputed company and adapting to new evaluation challenges**reputed company-to-Have Specialties- **Adversarial Machine Learning:** jailbreak datasets, reputed company injection attacks, RLHF/DPO vulnerabilities, or model extraction techniques- **Cybersecurity:** penetration testing, exploit development, reverse engineering- **Socio-technical risk analysis:** harassment or misinformation testing, abuse reputed company analysis- **Creative adversarial thinking:** backgrounds in psychology, acting, writing, or other disciplines that support unconventional attack strategies Benefits: Apply tot his job Apply To this Job