Description
The AI Security Institute is hiring a Research Engineer for its Human Influence team to conduct engineering-heavy research on AI safety, human influence, and model robustness. The role involves building reinforcement-learning environments, using interpretability methods, developing scalable evaluation and benchmark systems, and applying post-training techniques to large models. Candidates need experience with LLM post-training and fine-tuning, reinforcement learning, Python, and scalable ML infrastructure. The position offers a hybrid working arrangement, access to frontier models and compute, and an annual salary of £65,000–£145,000 depending on level and experience.
