Added
less than a minute ago
Location
Type
Full time
Salary
Upgrade to Premium to se...
Related skills
python machine learning ai llms evaluation📋 Description
- Lead research projects on detecting Claude misuse and strengthening safeguards.
- Design offline analyses of model usage to surface abuse patterns.
- Develop prototypes to feed signals into real-time safeguards with engineers.
- Study methods for detecting abusive behavior in chat-based workflows.
- Build evaluations to measure safeguards effectiveness.
- Publish findings to inform Trust & Safety, research, and product teams.
🎯 Requirements
- Independently drive research projects to concrete AI/ML results.
- Scope work and switch between research, engineering, and analysis.
- Familiar with how large language models operate: sampling, prompting, training.
- Proficient in Python and comfortable with large datasets.
- Care about AI's societal impacts and reducing real-world harm.
- Experience building ML models for abuse, fraud, or safety.
🎁 Benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
- Office space for collaboration
🛃 Visa sponsorship
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering 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!