Related skills
machine learning policy evaluation claude interpretability📋 Description
- Analyze real-world usage with observational tools to study Claude interactions.
- Build and run evaluations of Claude across key aspects of its Constitution.
- Collaborate with fine-tuning, safeguards, policy, and interpretability teams to improve models.
- Generate insights on societal impact to inform strategy and priorities.
- Publish research and present findings; develop tools for policymakers and researchers.
🎯 Requirements
- Experience with machine learning systems and infra for interfacing with models.
- Interest in societal impacts research; prior experience is a plus but not required.
- Adaptable and collaborative; able to follow team priorities.
- Skilled at writing up and communicating results, even if null or unexpected.
- Excited to partner with colleagues across teams on large-scale AI projects.
- Background in ML, data science, or a technical field with insights from complex systems.
🎁 Benefits
- Competitive compensation and benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
- Lovely office space in San Francisco
🛃 Visa sponsorship
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to All Other Jobs. Just set your
preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!