Senior Machine Learning Engineer, AI Safety

NVIDIA is seeking a Senior Machine Learning Engineer to support its AI Safety and Responsibility efforts for enterprise risk management. The role focuses on developing evaluation datasets, models, algorithms, and training approaches to improve the security, content safety, inclusivity, and alignment of multimodal large language models and agentic systems. The engineer will research and deploy model- and system-level safety techniques and collaborate cross-functionally with engineering, data science, and research teams.

Responsibilities:

• Evaluation: Develop datasets and specialized models & algorithms to evaluate/benchmark models & end-to-end systems in our core safety tracks (LLM Security, Agentic Safety, Content Safety, Hallucinations, and ML Fairness)
• Model Pre-Training, Mid-Training, Post-Training: Develop datasets and recipes for filtering training data, developing training datasets & recipes, including components like RL environments and teacher models, across our core safety tracks (LLM Security, Agentic Safety, Content Safety, Hallucinations, and ML Fairness)
• Model & system level techniques beyond post-training: Research & deploy new approaches, like Instruction Hierarchy or Risk Detection
• Cross-Functional Collaboration: Partner with engineers, data scientists, and research teams across NVIDIA to scale solutions for LLM Security, Agentic Safety, Content Safety, Hallucinations, and ML Fairness

Requirements:

• 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

• 4+ years of hands-on work experience in post-training of LLMs, including Supervised Fine-Tuning (SFT), Reinforcement Learning (RLHF/RLAIF), safety data generation techniques, ablation studies, and deploying models to production

• 1+ years of dedicated experience or research in at least one of the following areas:

  • LLM Security (backdoors, poisoning, latent behaviors).
  • Frontier Risks (deception, manipulation, loss-of-control).
  • Agentic Safety (LLM-level risks for multi-turn tool-calling/agents).
  • Multi-turn Safety Evaluation (dynamic and multi-turn alignment benchmarks)

• In-depth knowledge of machine learning principles and frameworks

• strong Python programming skills

• Experience working with large multimodal datasets and multi-modal foundational models

• Outstanding analytical problem-solving abilities paired with excellent collaboration and communication skills

• PyTorch preferred