Machine Learning Engineer, AI Safety

Anthropic is seeking a dedicated Machine Learning Engineer to join our AI Safety team. You will play a crucial role in developing and implementing techniques to ensure that advanced AI systems are safe, beneficial, and aligned with human values. This position requires a strong understanding of ML principles combined with a passion for AI safety research. **Responsibilities:** * Develop, implement, and evaluate machine learning models and algorithms focused on AI safety and alignment. * Contribute to research and development of techniques such as interpretability, robust AI, and detecting/mitigating harmful behaviors in AI systems. * Collaborate closely with AI researchers and other engineers to integrate safety considerations into the ML development lifecycle. * Analyze model behavior, identify potential risks, and propose mitigation strategies. * Contribute to the deployment and monitoring of AI systems with a focus on safety and reliability. **Qualifications:** * Master's or PhD in Computer Science, Machine Learning, or a related quantitative field, or equivalent practical experience. * Strong programming skills in Python and experience with ML libraries (e.g., PyTorch, TensorFlow). * Solid understanding of machine learning fundamentals, including deep learning. * Experience or demonstrated interest in AI safety, ethics, or responsible AI. * Ability to work independently and collaboratively in a fast-paced research environment. **Benefits:** * Competitive salary and equity package. * Comprehensive health, dental, and vision benefits. * Generous PTO and paid holidays. * Opportunity to contribute to cutting-edge AI safety research with a mission-driven company.