Sr. AI/LLM Threat Researcher, Agentic Systems - AI Detection and Response (Hybrid)

CrowdStrike

Hybrid

Quick summary

Work type
Hybrid
Location
Sunnyvale, CAAustin, TXRedmond, WA
Salary
$140,000–$215,000 / yr
Posted
7 days ago

Market check

Salary context

Below market

How this pay compares to similar roles

Similar $216k
This role $178k
$126k most similar roles pay here $272k

This role pays less than 78% of similar roles. Most pay $185,000–$246,687 — the shaded band above. At the midpoint, this role pays about $178k versus about $216k for comparable roles.

Based on 240 similar postings.

Employer

About CrowdStrike

CrowdStrike is a leading American cybersecurity technology firm, specializing in cloud-native endpoint protection, threat intelligence, and incident response.

CrowdStrike currently has 27 open roles on FindRole.

Listed pay typically runs $140,000–$215,000 across 27 roles with salary data.

Most-posted roles

View all roles at CrowdStrike

At a glance

TL;DR · Sr. AI/LLM Threat Researcher, Agentic Systems - AI Detection and Response (Hybrid)

As an AI Threat Researcher at CrowdStrike, you will join a dynamic team focused on large-scale distributed systems processing over 3 trillion daily events. Your role involves leading the identification and mitigation of threats to Large Language Models (LLMs) and AI Agents through deep analysis of LLM architectures and agentic frameworks, evaluating security in Agent-to-LLM interactions, developing robust testing methodologies for RAG pipelines, aligning research with industry standards like MITRE ATLAS, and contributing thought leadership via publications or conference presentations. You will need expertise in transformer architectures, AI orchestration frameworks, comprehensive knowledge of LLM prompts and protocols, proficiency in Python, and a deep understanding of evolving security threats. Bonus points include academic publications on AI/ML security, experience with red teaming, and developing defensive systems for agentic workflows.

What you'll do

  • Conduct deep-dive analysis to identify security weaknesses in LLM architectures and agentic frameworks.
  • Evaluate security boundaries in Agent-to-LLM and Agent-to-Application interactions to prevent manipulation.
  • Develop methodologies to test the robustness of RAG pipelines against adversarial inputs.
  • Map research findings to industry standards like MITRE ATLAS and OWASP Top 10 for LLM Applications.
  • Contribute to the security community by publishing whitepapers or presenting at industry conferences.

What we're looking for

  • Extensive experience in AI threat research and vulnerability analysis of LLMs.
  • Deep understanding of transformer architectures, attention mechanisms, and agentic systems security.
  • Proficiency in Python for developing custom red-teaming methodologies and evaluating AI security.
  • Knowledge of emerging AI protocols and the evolving LLM risk landscape.
  • Ability to map research findings to industry standards like MITRE ATLAS and OWASP Top 10 for LLMs.
  • Experience with AI orchestration frameworks and autonomous decision-making security implications.

More like this

Similar roles

Associate AI Security Researcher

Carnegie Mellon University

Pittsburgh, PA 146 days ago
Python Pytorch Tensorflow Numpy C C++ Ghidra IDA_Pro AI/ML cybersecurity CI/CD reverse_engineering vulnerability_assessment software_engineering Risk_Management policy_creation

Associate AI Security Researcher

Carnegie Mellon University

Pittsburgh, PA 48 days ago
Python Pytorch Tensorflow Numpy C C++ Ghidra IDA Pro AI/ML Cybersecurity CI/CD RE Vulnerability Assessment Security Research Technical Communication

AI Security Researcher

Carnegie Mellon University

Pittsburgh, PA 52 days ago
Python Pytorch Tensorflow Numpy C C++ Ghidra IDA Pro AI/ML Cybersecurity CI/CD Reverse Engineering Vulnerability Assessment Research Methodologies