Senior Deep Learning Scientist, AI Security

πŸ•’ Yesterday

πŸ‡ΊπŸ‡Έ United States – Remote

πŸ’΅ $187.5k - $442k / year

⏰ Full Time

🟠 Senior

🧠 AI Research Scientist

Where this job comes from

Posted on NVIDIA's careers page β†—NVIDIA's careers page, not through a job board

First seen by Remote Rocketship Yesterday

Still open on NVIDIA's site. Checked 23 minutes ago.

Apply Now
Logo of NVIDIA

NVIDIA

10,000+ employees

Founded 1993

πŸ₯ Healthcare

🏭 Manufacturing

πŸ€– Artificial Intelligence

Healthcare β€’ Manufacturing β€’ Artificial Intelligence

NVIDIA is a leading technology company specializing in accelerated computing and artificial intelligence. NVIDIA pioneers advancements in graphical processing units (GPUs), cloud computing, data centers, and virtual reality, with a focus on gaming, automotive, healthcare, and robotics industries. The company's innovations, such as NVIDIA Omniverse, transform traditional digital processes by enabling high-fidelity simulations and rendering tasks. Their applications span various industries, from autonomous vehicles using NVIDIA DRIVE to healthcare solutions with NVIDIA Clara, and AI-driven analytics and workflows.

πŸ“‹ Description

β€’ Apply fundamental and applied security research to develop, train, fine-tune, and deploy large language models for multimodal agentic reasoning systems and guardrails across text, audio, image, video, and tool usage β€’ Advance post-training and alignment methods including instruction tuning, preference optimization, RLHF/RLVR/MOPD β€’ Research and deploy model and system security techniques including instruction hierarchy, risk detection, and new cyber gyms β€’ Lead collection, development, and benchmarking of multimodal security datasets β€’ Ensure high-quality evaluation of model accuracy, safety, and task completion success β€’ Partner with engineers, data scientists, research teams, and product managers across NVIDIA to scale LLM security and agentic safety solutions

🎯 Requirements

β€’ Master’s degree (or equivalent experience) or PhD in Computer Science, AI, or Applied Math β€’ 8+ years of relevant work experience β€’ Excellent programming skills in Python β€’ Strong fundamentals in scalable model development β€’ Deep learning frameworks like PyTorch β€’ Strong knowledge of ML/DL techniques and modern foundation model architectures, including Transformers and mixture-of-experts models β€’ 1+ years of dedicated experience or research in at least one core safety area: LLM Security, Frontier Risks, Agentic Safety, or Multi-turn Security Evaluation β€’ Hands-on experience in post-training multimodal models for multimodal reasoning β€’ Experience or research involving LLM backdoors, data poisoning, latent malicious behavior, or structural model vulnerabilities β€’ Experience with advanced alignment challenges, model deception, manipulation, or loss-of-control scenarios β€’ Experience with multi-turn tool-calling, orchestration, and execution risks β€’ Experience with robust, scalable automated evaluation methodologies for conversational and iterative multi-turn use cases

πŸ–οΈ Benefits

β€’ Highly competitive salaries β€’ Comprehensive benefits package β€’ Equity β€’ Benefits for you and your family

Apply Now

πŸ“Š Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

πŸ•’ Yesterday

System Inc.

11 - 50

πŸ€– Artificial Intelligence

πŸ₯ Healthcare

πŸ”¬ Science

Senior Research Engineer designing LLM evaluation frameworks and benchmarks. System builds software helping healthcare teams see and solve complex systems.

πŸ•’ 3 days ago

Cisco

10,000+ employees

πŸ”§ Hardware

πŸ” Security

🏒 Enterprise

AI researcher developing resilient agent evaluation, training, and guardrails for Cisco’s AI infrastructure products. Building datasets, models, and reproducible experiments for production deployment.

πŸ•’ 3 days ago

Geolava

2 - 10

πŸ€– Artificial Intelligence

πŸ”Œ API

🀝 B2B

AI Researcher developing world models from geospatial and property data. Building forecasting capabilities for Geolava’s platform serving property and infrastructure decision-makers.

πŸ‡ΊπŸ‡Έ United States – Remote

πŸ”₯ Funding within the last year

πŸ’° Non-Equity Assistance on 2026-04

⏰ Full Time

🟠 Senior

🧠 AI Research Scientist

Cloud

Python

PyTorch

Remote Sensing

πŸ•’ November 11

TRM Labs

201 - 500

β‚Ώ Crypto

πŸ“‹ Compliance

🀝 B2B

AI Scientist building foundation models and autonomous agents on blockchain data. Powering TRM Labs’ crime-investigation and global-security intelligence products.

πŸ•’ November 11

Hook

11 - 50

πŸ“± Media

πŸ‘₯ B2C

Research Scientist developing generative audio and music ML models for Hook, a social music platform. Translating research into responsible, creative music tools.

Developed byΒ Lior Neu-ner. I'd love to hear your feedback β€” Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok