NVIDIA seeks a Senior AI Security Researcher to join its cutting-edge team, focusing on defining methodologies for testing, attacking, defending, and deploying frontier AI systems. This role involves developing innovative research questions and practical methods to uncover vulnerabilities in AI models, platforms, and autonomous agents, while also creating tools and evaluations that mitigate security risks. The ideal candidate will have extensive experience in AI security or related fields, with a proven track record of original research and practical impact, such as deploying security ML systems or identifying critical vulnerabilities. Proficiency in Python and modern ML/data tooling like PyTorch, TensorFlow, and Pandas is essential, along with expertise in areas like LLM security, adversarial ML, and secure deployment practices. The role demands strong cybersecurity skills, including threat modeling and vulnerability research, as well as the ability to translate complex findings into actionable recommendations for engineering teams.
Skills
Python
PyTorch
JAX
TensorFlow
scikit-learn
Pandas
NumPy
Spark
BigQuery
LLM security
adversarial ML
model evaluation
agent security
prompt injection
model backdoors
data poisoning
secure RAG
synthetic data
AI-enabled security automation
threat modeling
exploit research
malware analysis
network defense
threat hunting
detection engineering
digital forensics
incident-response automation
low-level systems security
What you'll do
Develop and answer open-ended AI security research questions for frontier models and systems.
Build practical methods and tools to reveal how AI systems can fail under adversarial conditions.
Explore various AI security issues such as LLM security, adversarial testing, and model evaluation.
Translate research findings into usable outcomes like proof-of-concept demonstrations and technical guidance.
Collaborate with cross-functional teams to connect research insights with NVIDIA's highest security priorities.
What we're looking for
12+ years of experience in AI security or related technical fields.
Demonstrated record of original research with practical impact in deployed systems.
Hands-on ability to build working research systems using Python and modern ML/data tooling.
Experience in multiple AI-security areas such as LLM security, adversarial ML, model evaluation.
Strong cybersecurity foundation including threat modeling, adversary simulation, exploit research.
Ability to translate ambiguous research problems into prioritized recommendations with measurable outcomes.
Published work or public technical leadership in AI security and related fields.
Market check
Salary context
This
$224,000–$356,500
range sits above
97%
of similar postings on FindRole.
Peer median band
$172,600–$259,350
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$165,950–$246,150
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
Employer
About Nvidia
Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing
Nvidia currently has
801 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 797 roles with salary data.
Locations Pittsburgh, Pennsylvania, US129 days ago
Python
Pytorch
Tensorflow
Numpy
C
C++
Ghidra
IDA Pro
AI/ML
Cybersecurity
CI/CD
Reverse Engineering
Vulnerability Assessment
Security Research
Tool Development
Framework Development
Methodology Evaluation
Technical Communication
Low-Level Programming
Mountain View, California, US43 days ago
$173,500–$234,500
Python
scikit-learn
R
SQL
Hive
SparkSQL
Linux
data mining
clustering
classification
regression
decision trees
neural nets
support vector machines
anomaly detection
recommender systems
sequential pattern discovery
text mining
A/B testing
statistical analysis