Senior Security Researcher (AI)

Origin HQ
Israel
Workplace: RemoteFull timeFunction: Research & Scientific (R&D)Experience: 5+ yearsSkills: ["Curiosity","Technical intuition","Hands-on experimentation","Communication","Adaptability"]

Investigate how adversaries evolve tradecraft to exploit and weaponize generative AI systems, including LLMs, on-device assistants, autonomous agents, code-generation models, and multimodal AI. Conduct hands-on research on adversarial prompting and jailbreak methods, then translate findings into actionable improvements for the endpoint AI observability platform. Publish public-facing security research and serve as a subject-matter expert supporting security operations and cross-team initiatives.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Origin HQ
Origin HQ
8 months ago

Senior Security Researcher (AI)

âś“ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 1 hour agoStatus: Live

Job Summary

Investigate how adversaries evolve tradecraft to exploit and weaponize generative AI systems, including LLMs, on-device assistants, autonomous agents, code-generation models, and multimodal AI. Conduct hands-on research on adversarial prompting and jailbreak methods, then translate findings into actionable improvements for the endpoint AI observability platform. Publish public-facing security research and serve as a subject-matter expert supporting security operations and cross-team initiatives.
Location: Israel
Workplace: Remote
Employment Type: Full time
Job Function: Research & Scientific (R&D)
Seniority: Mid level

Key Responsibilities

  • •Conduct in-depth research into how modern adversaries may evolve tradecraft to exploit or abuse generative AI tools, including LLMs, autonomous agents, and on-device assistants.
  • •Perform hands-on research into adversarial prompting, jailbreak methods, and tradecraft leveraging computer use agents and local models.
  • •Translate and implement research findings into actionable improvements for Origin’s products.
  • •Produce high-quality, public-facing security research content, including blog posts and conference talks.
  • •Act as a subject-matter expert in adversary tradecraft and security operations, supporting other business units and team-driven initiatives.

Pay and Benefits

Perks:Health InsurancePaid LeaveHome Office

Key Requirements

  • •5+ years of experience in offensive security research (e.g., red team operations, purple teaming) and/or defensive security research for publication and security feature development.
  • •Ability to write code for development of research tooling.
  • •Ability to explain complex technical concepts and research outputs to both executive-level and highly technical audiences.
  • •Demonstrated ability to convert ambiguous research signals into clear, actionable engineering outcomes.
  • •Aptitude for working in a fast-paced, adaptive startup environment.
Experience:5+ years
Skills:CuriosityTechnical intuitionHands-on experimentationCommunicationAdaptability
Tech Stack:LLMsGenerative AIPrompt engineeringJailbreaksAutonomous agentsOn-device assistantsComputer use agentsMultimodal AICode-generation modelsReinforcement learningModel interpretabilityModel exploitationAgentic misuseRed teamPurple teamingResearch toolingOperating system internalsReverse engineering

Company Brief

Origin HQ
Builds a security control validation and continuous visibility platform that tests, monitors, and validates endpoint and security tool effectiveness to help organizations know with certainty whether their defenses will stop modern threats.
Industry: Cybersecurity
Company Size: Small (11 to 50 employees)
Growth: Growth Stage Startup
Funding: Series A
Headquarters: New York, United States
Founded: 2020
Glassdoor
Glassdoor: 5.0
WebsiteLinkedInGlassdoor