Security Researcher (AI)

TL;DR

Security Researcher (AI) (Cybersecurity): Investigating the intersection of adversarial tradecraft and generative AI systems with an accent on LLM weaponization, autonomous agents, and adversarial prompting. Focus on translating research findings into defensive capabilities and producing high-quality security research content.

Location: Distributed team across the US, Canada, Australia, and Israel

Company

Origin (by hirify.global) is building an endpoint AI observability platform to maximize the productivity and safety of AI adoption within organizations.

What you will do

• Research how modern adversaries exploit generative AI tools, LLMs, and autonomous agents.
• Conduct hands-on research into adversarial prompting, jailbreak methods, and AI-enabled attack vectors.
• Translate research findings into actionable defensive improvements for Origin's products.
• Produce public-facing security research content, including blog posts and conference talks.
• Serve as a subject matter expert in adversary tradecraft to support internal business units.

Requirements

• 2+ years of experience in offensive (red/purple teaming) or defensive security research.
• Ability to write code for the development of research tooling.
• Ability to communicate complex technical concepts to both executive and technical stakeholders.
• Experience working in a fast-paced, adaptive startup environment.

Nice to have

• Experience investigating generative AI systems, prompt engineering, or agentic misuse.
• Familiarity with reinforcement learning, model interpretability, or safety research.
• Contributions to open-source AI or security tooling.
• Proficiency in systems languages (Rust, C/C++) and knowledge of OS internals or reverse engineering.

Culture & Benefits

• Culture of trust, autonomy, and high standards for top performers.
• Generous healthcare and flexible PTO.
• Home-office support for distributed team members.
• Environment that empowers team ownership and continuous improvement.