Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Horizon3

NewBe an early applicant

Senior Research Staff (Adversarial Intelligence)

Posted Updated

Description

  • We’re looking for an experienced Research Staff Member to join Horizon3 AI Research and lead research problems at the intersection of super intelligence, systems security, and agentic systems for security
  • You’ll identify and investigate technical problems that arise from real security environments and turn promising research directions into methods, prototypes, experiments, and systems that can influence Horizon3’s technology
  • Depending on the project, this may include AI agents for security, autonomous pentesting, attack-path reasoning, cyber deception, AI safety and security, security evaluation of AI systems, or new methods for reasoning over security data and environments
  • This is not a purely academic research role and it is not a conventional software engineering role
  • We are looking for someone who can move between research questions and working systems: define the problem, understand the relevant literature, develop a technical approach, build or guide implementation, design rigorous experiments, and determine what the results actually tell us
  • You do not need to be an expert in every area of AI and systems security
  • You should bring substantial technical depth in at least one of these areas, strong computer science foundations, and the ability to develop expertise quickly in unfamiliar domains
  • This role may be hired at the P3 (Career) or P4 (Senior) level based on experience, technical depth, independence, and demonstrated ability to lead complex research efforts
  • Identify, formulate, and drive research problems at the intersection of AI, cybersecurity, and computer systems
  • Translate real technical challenges from Horizon3’s products, security environments, and research agenda into well-defined research questions
  • Independently develop research directions, technical hypotheses, and experimental plans
  • Design and lead rigorous experiments in controlled and representative environments, with careful attention to assumptions, baselines, failure modes, and limitations
  • Build research prototypes and technical systems, or provide sufficient technical direction for others to implement and evaluate them
  • Study and evaluate modern AI techniques, including large language models, agentic systems, reasoning methods, learning algorithms, planning, search, and related approaches when relevant to the research problem
  • Reason over complex security data and environments, including attack paths, telemetry, graphs, configurations, identities, networks, cloud environments, and other heterogeneous system data
  • Read and critically evaluate academic and technical literature, identify gaps and useful ideas, and determine where existing methods do or do not apply to Horizon3’s problems
  • Develop evaluation methodologies that measure whether a proposed research approach actually works in realistic security settings
  • Work closely with attack engineers, security engineers, product teams, and other technical groups to understand operational constraints and evaluate research results
  • Provide technical mentorship and research guidance to junior Research Staff Members and interns
  • Help junior researchers refine research questions, evaluate technical approaches, interpret experimental results, and improve the quality of their work
  • Provide technical continuity for Lab projects and help guide research efforts when the Lab lead is unavailable
  • Communicate research findings clearly through technical reports, internal presentations, prototypes, and, when appropriate, academic publications or other external research outputs
  • Help shape future research directions for Horizon3 AI Research based on technical findings, emerging research, and Horizon3’s broader security challenges

Benefits

  • Growth Opportunities: Be part of a dynamic and growing team with numerous career advancement opportunities
  • Innovation-Driven Culture: Work in a collaborative environment that encourages creativity and out-of-the-box thinking
  • Inclusive and Diverse Team: We value diversity and promote an inclusive culture where everyone can thrive
  • Flexible Work Environment: Enjoy the convenience and work-life balance that comes with remote work
  • Interest in both research and engineering. You may have greater depth in one, but you should be able to operate effectively across research questions, experiments, prototypes, and real systems
  • Significant technical depth in systems security, super intelligence / machine learning, or a closely related area, along with the ability and motivation to work across AI and security
  • Ability to design rigorous experiments and evaluation methodologies, analyze results critically, and recognize when evidence does or does not support a conclusion
  • Demonstrated ability to independently identify, structure, and solve complex technical problems
  • Strong foundations in computer science, with the ability to reason deeply about algorithms, systems, software, and data
  • Ability to critically evaluate technical literature and quickly develop expertise in unfamiliar research areas
  • Strong programming and software engineering skills, with the ability to translate research ideas into working systems and prototypes
  • Ability to provide constructive technical guidance and mentorship to junior researchers without requiring formal people-management responsibility
  • Strong technical judgment, including the ability to reason about tradeoffs, assumptions, failure modes, risks, and unintended consequences
  • Experience conducting research or advanced technical investigation where the answer was not known in advance and success required careful experimentation and analysis
  • A degree in Computer Science or a related field, or equivalent technical experience
  • Ability to work independently while collaborating closely with researchers, engineers, product teams, and other technical stakeholders
  • Strong written and verbal communication skills, including the ability to explain complex technical ideas clearly to different audiences
  • Deep experience in one or more areas of 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 one or more areas of 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 projects from initial problem formulation through implementation, evaluation, and communication of results
  • Experience defining new research directions rather than only executing against an already-defined technical plan
  • Experience building research systems that operate on realistic environments, real-world data, or production-adjacent infrastructure
  • Familiarity with cybersecurity concepts such as attack paths, Active Directory, cloud environments, identity systems, security controls, adversarial techniques, and autonomous security systems
  • Experience designing experimental infrastructure, evaluation frameworks, benchmarks, or test environments for complex technical 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 is not required if the candidate can demonstrate comparable research and technical impact
  • Experience transferring research ideas into production systems or working closely with engineering teams to do so

Skills

Apply

See also