Senior Research Scientist, AI Safety and Security
Core
Leading research in AI safety and security, focusing on adversarial machine learning, model robustness, and securing next-generation AI models and agents against emerging threats.
Role type
Senior Research Scientist (AI Safety and Security)
Builds
Research techniques, evaluation benchmarks, and robust production solutions for trustworthy AI
Domain
Artificial Intelligence, Machine Learning, Cybersecurity
Deliverable
research
Required skills
Adversarial machine learning, ML interpretability, Generative models, Agentic AI, Multi-object optimization, ML safety, Continual learning, Red-teaming, Model backdoor detection, Prompt injection, Data poisoning
Preferred skills
Python programming, Investigating emerging technical threats (deepfakes, rogue agents), Debugging complex ML failure modes, Reverse engineering model behaviors
Technologies
Python, CVPR, ICCV, NeurIPS, ICML, ICLR
Responsibilities
Drive foundational ML research in model robustness and interpretability; Design and develop rigorous evaluation protocols and stress-testing methodologies; Curate advanced datasets and conduct fine-tuning experiments; Collaborate with engineering hubs and academic partners to transition proofs-of-concept into production; Publish groundbreaking research in ML venues.
