AI Researcher

AI Safety Researcher

Responsibilities

• Conduct research to improve the safety, reliability, and robustness of AI systems.
• Develop testing strategies for AI models, including adversarial and red teaming approaches.
• Design and implement evaluation tools and automated safety checks.
• Explore techniques such as interpretability, ethical alignment, and reinforcement learning from human feedback.
• Build benchmarks and datasets to assess model performance in real-world scenarios.
• Collaborate with engineering teams to integrate safety into AI system design and deployment.
• Contribute to open-source projects and internal tooling focused on AI safety.
• Investigate domain-specific safety challenges and help define standards for responsible AI use.

Qualifications

• Advanced degree in Computer Science, Machine Learning, or a related field.
• Experience with deep learning frameworks such as PyTorch or TensorFlow.
• Strong programming skills in Python.
• Familiarity with AI safety concepts, including robustness, bias mitigation, and model evaluation.
• Experience with adversarial testing or red teaming methodologies.
• Understanding of model deployment practices and monitoring in production environments.
• Research experience or publications in AI safety or related areas.