Senior Machine Learning Engineer, AI Safety

Develop safety evaluation and training techniques for large language models and autonomous AI systems at scale.
- Build datasets, models, and algorithms to evaluate LLM security, agentic safety, content safety, and multi-turn interactions.
- Design and implement post-training recipes including supervised fine-tuning, reinforcement learning, and safety data generation.
- Research novel safety approaches like instruction hierarchy and risk detection beyond standard post-training methods.
- Requires Master's or PhD in computer science or related field plus 8+ years ML engineering and 4+ years LLM post-training experience.
- Requires 1+ years dedicated work in LLM security, frontier risks, agentic safety, or multi-turn safety evaluation.

NVIDIA is a technology company that designs and manufactures GPUs and AI computing platforms used in data centers, gaming, and scientific research.