Responsibilities
- Investigate adversarial attacks, data poisoning, prompt injection, jailbreaks, and other AI system vulnerabilities in multi-modalities (e.g., text, image, video, and audio).
- Design and evaluate mitigation strategies, including fine-tuning, guardrails, content filtering, and robust model architectures.
- Develop and maintain AI security evaluation frameworks, datasets, and performance metrics.
- Partner with product and partnership teams to integrate the findings into our AI security solutions.
- Publish findings in top-tier conferences and journals, present at industry events, and contribute to open-source initiatives.
Benefits
- Competitive compensation
- Flexible working arrangements
- Professional growth opportunities
Additional Information
- Proficiency in multiple languages is a plus.
- Supports multiple Asian languages (Traditional Chinese, Simplified Chinese, Japanese, Korean, Thai) and Standard Arabic.
