Agentic Ai Safety Research Scientist

Advance agentic AI safety research at Amii through rigorous evaluations and applied machine learning expertise. Edmonton-based work supports safer autonomous systems.As an Applied Research Scientist, you will investigate risks in increasingly autonomous AI systems. You will develop evaluation methods, research experiments, and practical approaches addressing reliability, robustness, and oversight. The work includes agentic AI, machine learning systems, and AI safety priorities.Key Responsibilities:
Lead Trust and Safety research proposals focused on agentic AIDevelop evaluation pipelines, experiments, benchmarks, and testing environmentsTranslate findings into practical tools, frameworks, and methodologiesPublish papers, whitepapers, and scientific research outputsMentor researchers and collaborate across teams and institutionsRequirements:
Ph.D. in machine learning, artificial intelligence, computer science, or related fieldTwo-plus years of post-Ph.D. applied research experienceExperience evaluating machine learning systems and producing research outputsFamiliarity with agentic AI, LLM agents, tool use, and autonomyProficiency in Python and frameworks such as PyTorch, TensorFlow, or JAXApply your research leadership, evaluation expertise, and machine learning knowledge to Amii’s agentic AI safety program.
#J-18808-Ljbffr