Ai Research Engineer • Mid-Level

Who you are

You are a versatile professional who embodies both the roles of a scientist and an engineer, with a strong commitment to making AI systems safe, interpretable, and beneficial for society. You have a keen interest in exploring the challenges associated with human-level AI capabilities and are eager to contribute to exploratory research in AI safety. Your background includes experience in building and running machine learning experiments, and you are passionate about understanding and steering the behavior of powerful AI systems. You thrive in collaborative environments, working alongside researchers and engineers to tackle complex problems in alignment science.

You possess a solid understanding of AI control methods, focusing on ensuring that advanced AI systems remain safe and harmless, even in unfamiliar or adversarial scenarios. Your expertise extends to alignment stress-testing, where you create model organisms of misalignment to enhance empirical understanding of potential alignment failures. You are driven by a mission to create reliable AI systems and are excited about the opportunity to contribute to a team that prioritizes safety and ethical considerations in AI development.

What you'll do

In this role, you will be responsible for designing and executing thorough machine learning experiments that contribute to the understanding of AI alignment and safety. You will collaborate with interdisciplinary teams, including those focused on interpretability and fine-tuning, to explore innovative approaches to AI control. Your work will involve developing methods to assess and mitigate risks associated with powerful AI systems, ensuring that they operate safely in various contexts. You will also engage in research that informs the broader AI community about alignment challenges and solutions, contributing to Anthropic's mission of building beneficial AI systems.

What we offer

At Anthropic, you will be part of a rapidly growing team dedicated to advancing AI safety and alignment. We offer competitive compensation and benefits, including optional equity donation matching, generous vacation and parental leave, and flexible working hours. Our office in London provides a collaborative environment where you can engage with colleagues who share your commitment to creating safe and interpretable AI systems. Join us in our mission to ensure that AI technology is developed responsibly and ethically, making a positive impact on society.