About the role
The team identifies and mitigates risks from scientific superintelligence while preserving scientific discovery capabilities. The engineer develops and tests safeguards to reduce societal risks from advanced AI, working with scientists and engineers to implement effective interventions.
Our summary of the posting; the original is on the Lila Sciences careers page.
What the posting requires
- Required
- Research-engineering skills
- Safety post-training
- Model-level classifiers
- Safeguards
- Inference
- Abuse monitoring
- Enforcement
- Model-serving platform
- Safety interventions
- Model-development teams
- Preferred
- Scientific models
- Tool-using agents
- Scientific software
- Multi-step workflows
- Laboratory-connected systems
- High-consequence misuse
These tags are our reading of the posting. They can miss something; the original posting is the reference.