AI Safety Engineer

This role focuses on AI Safety for large language models, including content safety, bias detection, and adversarial robustness. The engineer will develop datasets and moderator models to ensure fairness and security in GenAI systems.

• Develop datasets and moderator models for Content Safety and ML Fairness
• Research bias detection and mitigation techniques
• Work on GenAI security aspects including prompt injection stability and adversarial robustness

• Strong background in machine learning and deep learning; experience with LLMs and generative AI; knowledge of AI safety and fairness.