AI Security Researcher (AI Security)

TL;DR

AI Security Researcher (AI Security): Conducting offensive security research on AI-powered applications, agentic systems, and browsers with an accent on prompt injection, tool abuse, agent manipulation, and data leakage. Focus on building testing frameworks and proof-of-concepts, performing penetration testing and architecture reviews, and producing reproducible vulnerability reports to help remediate risks across hirify.global’s AI ecosystem.

Location: Not specified

Company

hirify.global develops next-generation browser and AI-powered products.

What you will do

• Perform offensive security research against AI-powered applications, agentic systems, browsers, and emerging technologies.
• Investigate AI-specific attack vectors such as prompt injection, tool abuse, agent manipulation, and data leakage.
• Develop proof-of-concepts, testing frameworks, and research tooling to assess AI security risks.
• Run penetration testing, security assessments, and architecture reviews for AI-powered products.
• Write clear technical documentation, vulnerability reports, and reproducible research artifacts.
• Collaborate with product and engineering teams to remediate findings and improve security.

Requirements

• Hands-on experience in offensive security, penetration testing, vulnerability research, bug bounty programs, or red teaming.
• Proven ability to identify vulnerabilities and responsibly disclose them.
• Experience assessing AI systems, LLM applications, agentic frameworks, or related technologies.
• Strong programming skills to build tooling and automate testing workflows.
• Familiarity with prompt injection, AI abuse scenarios, model security, and emerging AI attack techniques.
• Excellent written communication skills for documenting technical findings clearly.

Nice to have

• Bug bounty achievements, CTF participation, or public security research.
• Experience with AI red teaming or adversarial testing.
• Open-source contributions related to security or AI.
• Familiarity with MCP, agent frameworks, vector databases, and modern AI application architectures.
• Security certifications or relevant academic background in cybersecurity or computer science.

Culture & Benefits

• Diverse, inclusive team with a supportive and collaborative environment.
• Flat structure with short decision-making paths.
• Ongoing skill development support.
• Applications reviewed on a rolling basis.
• Submit CV in English.

Hiring process

• Submit CV in English.
• Applications reviewed on a rolling basis.
• Recruitment process details available via the company’s FAQ.