Senior Deep Learning Scientist, AI Security
Core
Develop security alignment, guardrails, and adversarial defenses for large language models and multimodal agentic reasoning systems.
Role type
Senior Deep Learning Scientist (AI Security)
Builds
Secure multimodal agents, post-training alignment methods, and security datasets for NVIDIA's AI products.
Domain
AI Security / Large Language Models / Multimodal Systems
Deliverable
production ML models
Required skills
Python, PyTorch, Transformers, Mixture-of-Experts, RLHF/RLVR/MOPD, Auto Red-Teaming, Security Research, Multimodal Model Development
Preferred skills
Publications in NeurIPS/ICML/ICLR/CVPR/LLMSEC, Open-source contributions, Multilingual AI security experience
Technologies
PyTorch, Transformers, Mixture-of-Experts, RLHF, RLVR, MOPD
Responsibilities
Develop and deploy guardrails for LLMs; Research post-training alignment methods; Model and system security research; Collect and benchmark multimodal security datasets; Partner with engineering and product teams to scale security solutions.
Seniority
Senior, hands-on IC