Research Staff, Adversarial Intelligence
New
H
Horizon3.aiCybersecurity
US, RemoteFull-TimeEntry
SalaryBase salary range: $145,000 - $170,000 annually. Additional compensation: All full-time roles are eligible for an equity package in the form of stock options.
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonMachine LearningLLM
Requirements
- Have strong foundations in computer science, including algorithms, systems, software, and data.
- Bring technical depth in systems security, super intelligence / machine learning, or a closely related area.
- Have a strong interest in developing expertise across AI and security.
- Have strong programming skills and the ability to turn technical ideas into working implementations; Python experience is particularly useful.
- Be able to design careful experiments, analyze results, and distinguish evidence from intuition.
- Be curious and willing to investigate unfamiliar technical areas in depth.
- Be comfortable moving between technical ideas, experiments, prototypes, and implementation.
- Be able to receive technical feedback, revise approaches, and learn from researchers and engineers.
- Use sound technical judgment, including reasoning about assumptions, limitations, risks, and unintended consequences.
- Have strong written and verbal communication skills.
- Have a degree in Computer Science or a related field, or equivalent technical experience.
- Experience in systems security, offensive or defensive security, penetration testing, vulnerability research, operating systems, networks, distributed systems, or cloud security is a plus.
Responsibilities
- Conduct research on problems at the intersection of AI, cybersecurity, and computer systems.
- Formulate research questions from technical challenges faced by Horizon3 and its customers.
- Design and run experiments in controlled and representative environments.
- Build research prototypes and implement methods for meaningful evaluation.
- Study and evaluate modern AI techniques, including large language models, agentic systems, reasoning methods, and learning algorithms.
- Analyze security systems, attack paths, telemetry, graphs, configurations, and other real-world security data.
- Read and critically evaluate academic and technical literature and assess its relevance to research problems.
- Work with researchers, attack engineers, security engineers, product teams, and other technical groups.
- Document research methods, experiments, results, and limitations.
- Communicate findings through presentations, technical reports, prototypes, and, when appropriate, publications.
View Full Description & ApplyYou'll be redirected to the employer's site
