- RTP, North Carolina, United States
- $139K–$204K per year
- 7+ years
Operationalize transparency by building infrastructure to assess model behavior and ensure AI systems remain reliable, honest, and aligned.
Compensation
The starting salary range posted for this position is $139,300.00 to $203,600.00 and reflects the projected salary range for new hires in this position in U.S. and/or Canada locations, not including incentive compensation*, equity, or benefits.
Responsibilities
- Translate mechanistic interpretability concepts into scalable pipelines
- Build infrastructure to extract and interpret model activations
- Design red-teaming frameworks and automated behavioral auditing stress tests
- Partner with ML engineering to integrate transparency probes
- Track AI safety research and prototype new methods
Requirements
- Bachelor's degree in Computer Science or related field
- Master's degree in Computer Science or related field
- PhD in Computer Science or related field
- Nice to have: High proficiency in Python frameworks
- Nice to have: Distributed training
