Alignment Scientist / Engineer

• Conduct independent AI alignment research on pretraining, interpretability, and model safety approaches.
• Design and execute experiments decomposing complex problems into testable hypotheses using Python, PyTorch, and deep learning tools.
• Collaborate with external researchers to guide research direction and develop solutions.
• Build, train, and evaluate deep learning models using APIs and frameworks.

This role directly contributes to ensuring that advanced AI systems are safe and aligned with human values, reducing existential risks from AI.

• Strong background in deep learning and AI alignment research.
• Proficiency in Python and PyTorch.
• Experience designing and executing experiments with deep learning models.
• Ability to communicate technical work clearly and contribute to research publications.

Compensation and benefits are competitive and commensurate with experience. Specific details not provided in the posting.

AE Studio is a technology company that builds custom software and AI solutions, with a focus on impactful projects including AI safety research.