21 Nov
|
National Research Council Canada
|
Ottawa
21 Nov
National Research Council Canada
Ottawa
Shape frontier AI model assessment through reproducible benchmarks, scalable infrastructure, and transparent technical communication at the NRC.
As a mid-career RCO-04, you will establish the NRC’s AI Safety Lab, funded by the Canadian AI Safety Institute. The work spans evaluation frameworks, benchmark development, compute cluster operations, experiment documentation, and collaboration with government, research, and international partners. Technical findings will support practical tools, guidance, and policy recommendations.
Key Responsibilities:
- Steward standardized, reproducible safety evaluation protocols
- Curate benchmarks for advanced AI systems
- Monitor evaluations across frontier AI models
- Collaborate with NRC and CAISI safety researchers
- Provide actionable advice to practitioners and policymakers
Requirements:
- Master’s degree or qualifying bachelor’s degree with relevant experience
- Experience designing reproducible evaluation protocols and benchmarks
- Experience with compute clusters and scalable ML infrastructure
- Experience documenting experimental AI results
- Ability to communicate with technical and non-technical audiences
Use AI evaluation frameworks, infrastructure expertise, and communication skills to strengthen Canada’s advanced AI safety research.
#J-18808-Ljbffr
📌 Frontier AI Evaluation Program Manager (Ottawa)
🏢 National Research Council Canada
📍 Ottawa