AE Studio is a 160-person ML consultancy dedicated to solving the hardest problems in AI. They are seeking an Alignment Scientist/Engineer who is experienced in ML research and alignment research, passionate about AI alignment, and capable of working autonomously in fast-paced environments.
Responsibilities:
- Research a diverse set of ambitious alignment directions that others neglect, including pretraining interventions for model safety, novel interpretability techniques, neuroscience-inspired approaches to alignment, and many others
- Pair technical excellence with strong ownership of work
- Guide the direction of the research alongside collaborators
Requirements:
- Experienced in ML research, alignment research, or both
- Deeply passionate about AI alignment & believe genuine progress is possible
- Excellent at Python, Pytorch, and the modern deep learning stack
- Knowledgeable about building, training, or evaluating deep learning models
- Comfortable calling AI model APIs via REST or client libraries
- Adept at decomposing complex problems into concrete, testable experiments
- AI-native, and eager to use AI tools to automate your workflow
- Thrives in a fast-paced, startup-like environment
- Adept in English and comfortable communicating technical work to all audiences
- Experience performing self-directed research or data science projects (show us what you've built, especially if it increases human agency)
- Software engineering background and best practices
- Agile experience (Kanban, Scrum, XP)
- Experience managing clients and client relationships
- Experience in startups
- Being in LA to work from our office