Ottawa Postdoctoral Fellow Trustworthy Ai
Save this job and keep your search organized
Create a free account to save jobs, create alerts and return to this listing from your dashboard.
By continuing, you agree to our Terms & Privacy Policy.
Research trustworthy AI in Ottawa through uncertainty quantification for large language models. Work with LLM interpretability and evaluation methods.
The National Research Council offers a two-year Postdoctoral Fellowship in Digital Technologies. You will work autonomously under guidance from an NRC researcher, developing uncertainty signals for outputs and encoded concepts. Applications include hallucination detection, safety failure mitigation, synthetic content detection, and improved evaluation.
Key Responsibilities:- Design novel research on uncertainty in generative AI
- Examine uncertainty in human-interpretable model concepts
- Develop applications for hallucination and synthetic content detection
- Investigate safety failure mitigation and evaluation improvements
- Collaborate with related LLM interpretability and evaluation work
- PhD completed recently or expected within six months
- AI research experience with novel project implementation
- Deep learning library experience for data analysis or simulation
- Significant publication contributions at high-calibre venues
- Understanding uncertainty quantification or mechanistic interpretability is an asset
Build research expertise in trustworthy AI by connecting LLM interpretability, uncertainty methods, and impactful evaluation applications.
#J-18808-Ljbffr