Pioneer AI Security Offensive Engineer

Hitachi Cyber; United States; On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Frontier AI focus

Specialized AI security training

Mentorship within global cyber team

Global cybersecurity organization

Job summary

Hitachi Cyber is seeking an experienced penetration tester for its Frontier AI Security practice. You will apply offensive security to AI systems, including LLMs, RAG pipelines, and AI agents.

Your role includes scoping, threat modeling (MITRE ATLAS/OWASP LLM Top 10), and adversarial testing across AI-powered applications. You will document findings and drive remediation with client engineering and security leadership.

Qualifications

• 5+ years of hands-on experience conducting penetration testing engagements across web applications, APIs, mobile applications, cloud environments, or network infrastructures.
• Bachelor's degree in a technical field or equivalent demonstrated experience.
• Strong expertise in at least one offensive security domain: web/API, infrastructure and AD, mobile, or cloud configuration review.
• Demonstrated ability to identify and bypass security controls and clearly articulate attack methodologies and findings.
• Experience performing source-assisted testing, including architecture documentation review to identify attack paths.
• Practical scripting experience with Python and strong Linux proficiency.
• Experience delivering client-facing reports and presenting findings to technical and business stakeholders.
• Excellent written communication skills and experience producing professional reports and deliverables.

Responsibilities

• Lead the scoping and rules of engagement for AI security validation assessments.
• Develop threat models for AI systems using MITRE ATLAS and OWASP LLM Top 10, and define testing objectives with clients.
• Conduct adversarial testing against AI-powered systems, including prompt injection and RAG-related scenarios.
• Execute adaptive attack campaigns and validate AI security controls and guardrails.
• Assess and document effectiveness of AI security controls and remediation actions.
• Prepare and present technical findings and prioritized remediation to client teams.

Skills

Penetration testing

Python scripting

Linux

Client-facing reports

Security testing

Education

Bachelor's degree in a technical field

Tools

Caido

Burp Suite

Python-based testing frameworks

Job description

Hitachi Cyber is seeking an experienced penetration tester for its Frontier AI Security practice. You will apply offensive security to AI systems, including LLMs, RAG pipelines, and AI agents.

Your role includes scoping, threat modeling (MITRE ATLAS/OWASP LLM Top 10), and adversarial testing across AI-powered applications. You will document findings and drive remediation with client engineering and security leadership.