Alignment Scientist/Engineer

AE Studio is seeking an Alignment Scientist/Engineer to join its alignment research team, working on high-upside, under-resourced projects with real autonomy. The team collaborates with researchers at leading organizations such as Anthropic, Princeton, and UCL, conducting research to ensure AI systems remain aligned. This is a remote-first, full-time role with a competitive salary for US-based candidates.

• Join the alignment research team on projects selected for high upside and under-resourced status
• Conduct real alignment research with autonomy in directions most organizations aren't set up to pursue
• Collaborate with external visionaries and researchers, with weekly conversations to keep projects moving
• Break complex problems into concrete experiments and execute them independently or with the team

• Experience with ML research, alignment research, or both
• Strong Python skills and experience building, training, or evaluating deep learning models (NLP, vision, or LLMs)
• Experience calling AI model APIs via REST or client libraries
• Ability to break complex problems into concrete experiments
• Comfortable in a fast-paced, startup-like environment
• Clear communicator in English who can explain technical work to non-technical audiences