Senior AI Safety Engineer: LLM Security & Multimodal Risk

Remote Jobs; United States; Remote; USD 184,000 - 288,000; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA seeks Deep Learning Scientists, AI Researchers, and Machine Learning Engineers to join AI Safety and Responsibility for Enterprise Risk Management. You will tackle scalable safety for multi-modal LLMs, focusing on security, content safety, and inclusivity across frontier risk areas.

You will collaborate with NVIDIA teams to benchmark models, design safety datasets, and deploy safety-aware pipelines, with a strong emphasis on responsible AI and cross-functional impact.

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 of hands-on work in post-training of LLMs, including SFT, RLHF/RLAIF, and production deployment.
• Core Safety Expertise: 1+ years in at least one of: LLM Security, Frontier Risks, Agentic Safety, Multi-turn Safety Evaluation.
• Technical Mastery: In-depth knowledge of ML principles and frameworks (PyTorch preferred) with strong Python programming skills.
• Multimodal Systems: Experience with large multimodal datasets and multimodal foundational models.
• Soft Skills: Excellent analytical, collaboration, and communication abilities.
• Cultural Alignment: Humility, transparency, respect, and intellectual honesty.

Responsibilities

• Evaluation: Develop datasets and models to evaluate/benchmark safety tracks (LLM Security, Agentic Safety, Content Safety, Hallucinations, ML Fairness).
• Model Training: Create datasets and recipes for filtering data and training pipelines across safety tracks.
• Model & System Techniques: Research and deploy new approaches beyond post-training (e.g., Instruction Hierarchy, Risk Detection).
• Cross-Functional Collaboration: Partner with engineers, data scientists, and research teams to scale safety solutions.

Skills

Python programming

PyTorch

Multimodal data handling

Analytical problem solving

Collaboration & communication

Education

Master's or PhD in CS/EE or related field

Tools

PyTorch

Python

Job description

NVIDIA seeks Deep Learning Scientists, AI Researchers, and Machine Learning Engineers to join AI Safety and Responsibility for Enterprise Risk Management. You will tackle scalable safety for multi-modal LLMs, focusing on security, content safety, and inclusivity across frontier risk areas.

You will collaborate with NVIDIA teams to benchmark models, design safety datasets, and deploy safety-aware pipelines, with a strong emphasis on responsible AI and cross-functional impact.