Senior ML Engineer, AI Safety & LLM Security | Equity

NVIDIA AI; Santa Clara (CA); On-site; USD 184,000 - 288,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking talented Deep Learning Scientists / AI Researchers / Machine Learning Engineers to join our rapidly growing AI Safety and Responsibility efforts for Enterprise Risk Management. In this role, you will tackle innovative problems in machine learning, focusing on scaling safety for multi-modal LLMs and agentic safety across NVIDIA's frontier models.

You will collaborate with engineers and researchers across NVIDIA to develop datasets, training recipes, and evaluation methodologies

Qualifications

• Master's or PhD in Computer Science, Electrical Engineering, or related quantitative field.
• 8+ years of proven experience in systems software engineering or machine learning engineering.
• 4+ years of post-training experience with LLMs (SFT, RLHF/RLAIF) and safety data generation techniques.
• 1+ years of dedicated experience in LLM safety areas (LLM Security, Frontier Risks, Agentic Safety, Multi-turn Safety Evaluation).
• Strong knowledge of ML principles and Python; experience with multimodal models.

Responsibilities

• Develop datasets and models to evaluate and benchmark safety tracks (LLM Security, Agentic Safety, Content Safety, Hallucinations, ML Fairness).
• Develop datasets and recipes for filtering training data and creating training datasets across safety tracks.
• Research and deploy new approaches such as Instruction Hierarchy or Risk Detection.
• Collaborate with engineers, data scientists, and research teams across NVIDIA to scale safety solutions for LLMs.

Skills

Python programming

PyTorch

Multimodal datasets

Research collaboration

Education

Master's or PhD in Computer Science or Electrical Engineering

Tools

PyTorch

Python

Job description

NVIDIA is seeking talented Deep Learning Scientists / AI Researchers / Machine Learning Engineers to join our rapidly growing AI Safety and Responsibility efforts for Enterprise Risk Management. In this role, you will tackle innovative problems in machine learning, focusing on scaling safety for multi-modal LLMs and agentic safety across NVIDIA's frontier models.

You will collaborate with engineers and researchers across NVIDIA to develop datasets, training recipes, and evaluation methodologies