Advance agentic AI safety research at Amii in Edmonton, focusing on rigorous evaluations, autonomous systems, and practical risk-mitigation tools.

The Applied Research Scientist will lead Trust and Safety research on increasingly autonomous AI systems. You will investigate safety challenges, develop evaluation methodologies, and study reliability, robustness, and oversight. The work includes experiments, publications, open-source tools, and applied research outputs.

Key Responsibilities:

- Lead research proposals focused on agentic AI safety
- Develop evaluation pipelines, benchmarks, and testing environments
- Investigate unintended behaviours, oversight, and emerging risks
- Translate findings into practical tools and methodologies
- Author papers,



whitepapers, and scientific outputs

Requirements:

- Ph.D. in machine learning, artificial intelligence, or related field
- Two-plus years post-Ph.D. applied research experience
- Experience evaluating machine learning systems and producing research outputs
- Solid knowledge of agentic AI and autonomous decision-making
- Proficiency in Python and ML frameworks

Apply your research leadership, evaluation expertise, and machine learning knowledge to advance safer agentic AI systems at Amii.

📌 Applied Research Scientist Agentic AI Safety (Edmonton)
🏢 Alberta Machine Intelligence Institute
📍 Edmonton