Full Job Description
Senior Deep Learning Scientist, AI Safety
What you will be doing:
• Apply fundamental and applied safety research to develop, train, fine-tune, and deploy large language architectures supporting multimodal agentic reasoning systems and guardrails encompassing text, audio, image, video, and tool usage.
• Advance post-training and alignment methods including instruction tuning, preference optimization, and RLHF/RLVR/MOPD to improve safety of multimodal agents for complex use cases.
• Research and advance the latest trends in AI safety as applied to pre-/mid-/post-training, guardrails, and steering techniques.
• Lead the collection, development, and benchmarking of multimodal safety datasets, ensuring high-quality evaluation of model accuracy, safety, and task completion success.
What we need to see:
• Master's degree (or equivalent experience) or PhD in Computer Science, AI, or Applied Math with 8+ years of relevant work experience.
• Excellent programming skills in Python with strong fundamentals in scalable model development and deep learning frameworks like PyTorch.
• Strong knowledge of ML/DL techniques and modern foundation model architectures, including Transformers and mixture-of-experts models.
• Hands-on experience in post-training multimodal models for multimodal reasoning.
• Proven ability to manage model development life cycles, including dataset versioning, experiment tracking, and evaluation pipelines.
• Responsible AI Expertise: 1+ years of experience in content safety, ML fairness, AI model security, human-AI interaction, or related areas.
Ways to stand out from the crowd:
• Strong record of publications in top-tier AI and machine learning venues such as NeurIPS, ICML, ICLR, FAccT, or CVPR.
• Experience applying deep reinforcement learning techniques to train multimodal agents in complex simulation.
• Safety and Compliance: Proven experience addressing safety and legal and regulatory compliance in multimodal, multilingual, or multi-turn systems.
• Multi-turn Safety Evaluation: dynamic and multi-turn alignment benchmarks.
• Experience in at least one of the following risk areas: CBRNE, persuasion and manipulation (influence operations, disinformation, and the erosion of democratic values through AI-generated content), discrimination at scale enabled by AI systems, mental health (sycophancy and manipulation), LLM security (backdoors, data poisoning, latent malicious behavior, structural model vulnerabilities), frontier risks (model deception, manipulation, and loss-of-control scenarios), agentic safety (tool-calling, orchestration, and execution), multi-turn.
Your base salary will be determined based on your location, experience, and other objective job-related factors. The expected base salary ranges for this position are:
183,750 USD - 351,000 USD for Level 4; and 225,000 USD - 429,000 USD for Level 5.
You will also be eligible for equity and benefits.
Applications for this job will be accepted at least until November 20, 2026.
This posting is for an existing vacancy.
NVIDIA uses AI tools in its recruiting processes.