AI/Cyber Researcher

General Analysis; San Francisco (CA); Hybrid; USD 140,000 - 210,000; Full time

Job summary

General Analysis is a frontier security lab focused on evaluating and strengthening frontier AI models against cyberdefense threats. You will lead research into measuring capabilities, mitigating misuse, and developing evaluation methodologies across real-world scenarios and collaborations with red teams and security firms.

The AI/Cyber Researcher role emphasizes publishing findings, expanding diverse evaluation challenges, and translating complex research into practical protections for

Qualifications

• Background in vulnerability or security research (CTF, CVEs, malware analysis) or deep research with frontier AI models.
• Ability to design/implement novel research approaches for emerging AI security challenges.
• Publications in top venues (e.g., NeurIPS, ICML, ICLR, USENIX Security) or equivalent applied work.

Responsibilities

• Advance research on evaluating and mitigating risks from AI misuse and security threats.
• Develop novel evaluation challenges including CTF-style tasks and simulated network attacks.
• Collaborate with red teamers, pentesters, and contracted firms to ground challenges in real-world difficulty.
• Publish results in blogs and academic venues and communicate findings to customers.

Skills

Security research

Vulnerability research

CTF

Malware analysis

Offensive tooling

AI frontier models

Job description

General Analysis is a frontier security lab. We protect the world as AI systems grow more capable and more dangerous in the wrong hands. We build high-fidelity research infrastructure that evaluates and strengthens frontier models on critical cyberdefense tasks, and we bring that research directly to enterprises — securing the AI systems they deploy through adversarial testing and runtime protection.

About the role

As an AI/Cyber Researcher, you will help shape the future of AI security evaluation. In this role, you will push the frontier of knowledge on what frontier models can do, how to measure it, and how to mitigate dangerous capabilities.

You will expand the quantity, quality, and diversity of our evaluation challenges, from original CTF-style exploitation tasks to network attack simulations and entirely novel classes of security challenges.

You will collaborate with expert red teamers, pentesters, and contracted security firms to ground these challenges in real-world difficulty.

You will research capability elicitation and jailbreak methods, and develop methodologies for assessing generalization and coverage in our evaluations.

Your work will engage the open questions no one else is equipped to answer: Can an AI find and exploit 0-days? Can an AI elevate an average computer science student's cyber capabilities to those of a nation-state?

You will lead research into mitigating risks from AI misuse, model weight theft, and loss of control.

From time to time, you will publish results in blog posts and academic venues, and deliver findings directly to customers.

You may be a good fit if

• You have a strong background in vulnerability or security research, such as CVEs, CTF competitions, malware analysis, or offensive tooling, or deep research experience with frontier AI models.
• You can design and implement novel research approaches for emerging AI challenges.
• You have publications in top-tier venues such as NeurIPS, ICML, ICLR, or USENIX Security, or a track record of comparable applied work.
• You have a high level of agency, strong technical acumen, and clarity of thought.

You'll thrive here if

• You are excited about applying novel research and new technology to real-world problems.
• You are excited to learn new domains and build deep context in AI security.
• You are results-oriented and can balance deep exploration with practical implementation.
• You proactively step outside defined boundaries to support the team's mission and unblock others.