Trustworthy AI Scientist, Centre for Frontier AI Research, IAIC
Core
Conduct R&D on the safety of generative AI and multi-agent systems, developing scientific evidence, testing tools, and guidance for safe deployment in real-world clinical settings.
Role type
Research scientist (AI safety)
Builds
Regulatory-grade toolkits, testing tools, and safety guidance for clinical GenAI and multi-agent systems
Domain
Healthcare + AI safety
Deliverable
research
Required skills
Python, deep learning frameworks (PyTorch), adversarial machine learning, LLM/VLM research, red-teaming, hallucination detection, uncertainty quantification
Preferred skills
None stated
Technologies
PyTorch, LLMs, VLMs
Responsibilities
Design and conduct systematic red-teaming and risk assessments of GenAI systems; Develop efficient guardrails and risk-mitigation methods; Develop methods for continuous post-deployment monitoring
Seniority
Senior, research-focused IC
