Senior Research Staff, Adversarial Intelligence

Horizon3

1d•$174,191 - $249,230•Remote

About The Position

Horizon3 is seeking an experienced Research Staff Member to join Horizon3 AI Research and lead research at the intersection of super intelligence, systems security, and agentic systems for security. The role identifies technical problems arising in real security environments and turns promising research directions into methods, prototypes, experiments, and systems that can influence Horizon3's technology. Research areas may include AI agents for security, autonomous pentesting, attack-path reasoning, cyber deception, AI safety and security, evaluation of AI systems, and methods for reasoning over security data and environments. This is neither a purely academic research role nor a conventional software engineering role. The Research Staff Member moves between research questions and working systems: defining problems, assessing relevant literature, developing technical approaches, building or guiding implementation, designing rigorous experiments, and interpreting results. The candidate should bring substantial depth in at least one relevant AI or systems security area, strong computer science foundations, and the ability to develop expertise in new domains. Hiring may be at P3 (Career) or P4 (Senior), based on experience, technical depth, independence, and ability to lead complex research efforts. The role is fully remote and may require up to 5% travel. The stated annual base salary range is $174,191–$249,230, with the exact amount depending on location, qualifications, experience, and skills. Full-time employees are eligible for stock options. Horizon3 offers health, vision, and dental insurance, a flexible vacation policy, and generous parental leave.

Requirements

Strong computer science foundations and the ability to reason deeply about algorithms, systems, software, and data.
Significant technical depth in systems security, super intelligence or machine learning, or a closely related area, and motivation to work across AI and security.
Demonstrated ability to independently identify, structure, and solve complex technical problems.
Experience conducting research or advanced technical investigation where the answer was not known in advance and success required careful experimentation and analysis.
Strong programming and software engineering skills, including the ability to turn research ideas into working systems and prototypes.
Ability to design rigorous experiments and evaluation methodologies, critically analyze results, and recognize whether evidence supports a conclusion.
Ability to critically evaluate technical literature and quickly develop expertise in unfamiliar research areas.
Interest in both research and engineering, with the ability to work across research questions, experiments, prototypes, and real systems.
Strong technical judgment, including the ability to reason about tradeoffs, assumptions, failure modes, risks, and unintended consequences.
Ability to provide constructive technical guidance and mentorship to junior researchers without formal people-management responsibility.
Ability to work independently and collaborate with researchers, engineers, product teams, and other technical stakeholders.
Strong written and verbal communication skills, including the ability to explain complex technical ideas to different audiences.
A degree in Computer Science or a related field, or equivalent technical experience.

Nice To Haves

Deep experience in systems security, offensive security, defensive security, penetration testing, vulnerability research, operating systems, networks, distributed systems, cloud security, identity systems, or related fields.
Deep experience in machine learning, deep learning, large language models, AI agents, reinforcement learning, planning, search, graph reasoning, program analysis, or related AI and systems methods.
Experience leading or substantially contributing to research from problem formulation through implementation, evaluation, and communication of results.
Experience defining new research directions rather than only executing an established technical plan.
Experience building research systems for realistic environments, real-world data, or production-adjacent infrastructure.
Experience designing experimental infrastructure, evaluation frameworks, benchmarks, or test environments for complex technical systems.
Familiarity with cybersecurity concepts such as attack paths, Active Directory, cloud environments, identity systems, security controls, adversarial techniques, and autonomous security systems.
Experience mentoring junior researchers, engineers, students, or interns.
Strong research publications, patents, conference presentations, open-source contributions, or other evidence of high-quality technical work. A strong publication record is valuable but not required when comparable research and technical impact can be demonstrated.
Experience transferring research ideas into production systems or working closely with engineering teams to do so.

Responsibilities

Identify, formulate, and drive research problems at the intersection of AI, cybersecurity, and computer systems.
Translate technical challenges from Horizon3 products, security environments, and research agendas into well-defined research questions.
Independently develop research directions, technical hypotheses, and experimental plans.
Design and lead rigorous experiments in controlled and representative environments, accounting for assumptions, baselines, failure modes, and limitations.
Build research prototypes and technical systems, or provide technical direction for their implementation and evaluation.
Study and evaluate modern AI techniques, including large language models, agentic systems, reasoning methods, learning algorithms, planning, and search, as relevant to research problems.
Reason over complex security data and environments, including attack paths, telemetry, graphs, configurations, identities, networks, and cloud environments.
Read and critically evaluate academic and technical literature, identify gaps and useful ideas, and assess the applicability of existing methods to Horizon3's problems.
Develop evaluation methodologies to assess whether research approaches work in realistic security settings.
Work with attack engineers, security engineers, product teams, and other technical groups to understand operational constraints and evaluate research results.
Mentor junior Research Staff Members and interns by guiding research questions, technical approaches, experiments, and interpretation of results.
Provide technical continuity for Lab projects and help guide research when the Lab lead is unavailable.
Communicate findings through technical reports, internal presentations, prototypes, and, when appropriate, publications or other external research outputs.
Help shape future research directions based on technical findings, emerging research, and Horizon3's security challenges.