145K–170K USD / year
Research Staff, Adversarial Intelligence
AIRemote — United States
Published on 2026-11-05
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
Research AI, cybersecurity, and computer-systems problems, translating ideas into experiments, prototypes, and practical methods. Projects may involve AI agents for security, autonomous penetration testing, attack-path reasoning, or security evaluation of AI systems.
About the company
Horizon3.ai is a technology company specializing in cybersecurity solutions, focusing on automated penetration testing and threat detection for enterprises. They provide a range of services aimed at enhancing security posture and risk management for organizations across various sectors.
The team
Horizon3 AI Research, within AI Labs.
Stack
PythonLarge language modelsAI agentsMachine learningReinforcement learning
What you'll do
- Formulate research questions based on real security challenges.
- Design and run experiments, analyze results, and document methods and limitations.
- Build research prototypes and evaluate AI techniques and security systems.
- Review technical literature and communicate findings through reports, presentations, and, where appropriate, publications.
- Collaborate with researchers, attack and security engineers, and product teams.
What we're looking for
- Strong computer science foundations and technical depth in systems security, machine learning, or a related area.
- Strong programming skills and the ability to implement technical ideas.
- Ability to design careful experiments and assess results rigorously.
- Interest in both research and engineering, with a willingness to develop expertise across AI and security.
- Strong written and verbal communication skills.
- Computer Science degree or related field, or equivalent technical experience.
Nice to have
- Experience in cybersecurity, penetration testing, vulnerability research, operating systems, networks, or cloud security.
- Experience with LLMs, AI agents, reinforcement learning, planning, search, or graph-based reasoning.
- Research experience, publications, open-source work, or experience building benchmarks and evaluation frameworks.
- Familiarity with attack paths, Active Directory, cloud environments, identity systems, or network security.
Benefits
- Stock options
- Health, vision, and dental insurance for employees and family
- Flexible vacation policy
- Generous parental leave