The Opportunity: AI Security Researcher

We are looking for an AI Security Researcher with a strong offensive security mindset, published CVEs, and the ability to use AI as a hacking tool. The core of this role is finding real exploitable issues before attackers do, prioritizing external (internet-facing) exploits, then internal ones.

You will build autonomous agents that research and hack on the fly by interacting with AI, and you will jailbreak AI systems.

The ideal candidate has a strong offensive security background, has already shifted to using AI to find bugs, and is already hands-on and comfortable working this way.

Key Responsibilities

- Proactively find, exploit, and document real-world vulnerabilities, prioritizing external (internet-facing) attack paths, then internal ones.
- Discover these issues before attackers do, with working proofs of concept and demonstrated impact.
- Build autonomous agents that hunt, attack, and iterate on the fly by interacting with AI models and tools.
- Use and develop AI-driven offensive workflows (multi-model setups, tool-calling, notebooks, orchestration) for continuous hunting.
- Apply deep offensive security skills (API abuse, authentication and access control, secrets, misconfiguration, red teaming) with AI in the loop.
- Produce CVE-quality research outcomes and drive findings through to engineering fixes.
- Design, execute, and document jailbreaks, prompt injection attacks, model evasion, data exfiltration, and other offensive techniques against AI systems.
- Assess and attempt to compromise Model Context Protocol (MCP)–based systems and other tool-calling / plugin ecosystems.
- Build and automate security testing workflows involving multiple models, APIs, and tools (e.g., Jupyter notebooks, orchestration frameworks).
- Perform offensive security testing and red teaming of AI-driven products, including API manipulation and integration abuse.
- Research security weaknesses in models and the infrastructure around them.
- Contribute to in-house guardrail design: define, implement, and test safety and security guardrails for models and AI automations.
- Propose and evaluate defensive controls: input/output filtering, policy enforcement, monitoring, anomaly detection, and non-AI controls to secure AI systems.
- Translate research findings into practical engineering requirements and collaborate closely with product and engineering teams to implement fixes and mitigations.
- Work with multiple teams, explain risk and impact clearly, and present findings to different teams and C-level stakeholders.
- Produce clear technical documentation, proof-of-concepts, and knowledge sharing on AI security practices and new attack/defense techniques.

What you'll Need to Succeed:

Must have
- Bachelor's in Computer Science or related degree.
- 2–7 years in offensive cybersecurity.
- Published CVE(s).
- Strong offensive security knowledge: API security testing and manipulation; prior red teaming, penetration testing, or adversarial testing.
- Hands-on jailbreak experience (prompt injection, role confusion, data leakage, safety bypasses, and similar).
- Ability to work with multiple teams, explain risk and impact, and present to different teams and C-level stakeholders.
- Good communication skills in English.
- Experience handling and maintaining production-level code.

Strongly recommended
- Proven exploits or write-ups that used AI (models/agents) to find or exploit bugs.
- Experience building autonomous agents that interact with AI to attack or test systems on the fly.
- Already using AI in day-to-day offensive work to find bugs, and comfortable with that shift.
- Bug bounty / HackerOne or similar track record.
- Conference presentations.