Senior AI Safety & LLM Security Engineer

NVIDIA Corporation; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Job summary

NVIDIA Corporation is seeking talented Deep Learning Scientists, AI Researchers, and ML Engineers to join our AI Safety and Responsibility efforts for Enterprise Risk Management. The role focuses on scaling safety for multi-modal LLMs and advancing agentic safety across NVIDIA’s AI stack.

Required: Master’s/PhD in a quantitative field, 8+ years in ML or systems software, 4+ years post-training LLM experience, strong Python and PyTorch skills, and expertise in LLM safety and multimodal data.

Qualifications

• Master’s or PhD in Computer Science, Electrical Engineering, or a related quantitative field (or equivalent experience).
• 8+ years of proven experience in systems software engineering or machine learning engineering.
• Post-Training Experience: 4+ years in post-training of LLMs, including SFT, RLHF/RLAIF, data generation, ablation studies, production deployment.

Responsibilities

• Evaluate models and end-to-end systems across safety tracks (LLM Security, Content Safety, Hallucinations, ML Fairness).
• Develop datasets and recipes for training data filtering and RL environments.
• Design and deploy new safety techniques beyond post-training (e.g., instruction hierarchy).
• Collaborate cross-functionally with engineers and researchers to scale safety solutions.

Skills

Python

PyTorch

Multimodal data

LLM safety

RLHF/RL from data

Education

Master's or PhD in CS/EE

Tools

PyTorch

Job description

NVIDIA Corporation is seeking talented Deep Learning Scientists, AI Researchers, and ML Engineers to join our AI Safety and Responsibility efforts for Enterprise Risk Management. The role focuses on scaling safety for multi-modal LLMs and advancing agentic safety across NVIDIA’s AI stack.

Required: Master’s/PhD in a quantitative field, 8+ years in ML or systems software, 4+ years post-training LLM experience, strong Python and PyTorch skills, and expertise in LLM safety and multimodal data.