AI Security Engineer / Architect

About o9 Solutions

Role Overview

What You'll Do

• Design and execute AI-specific VAPT engagements involving prompt injection chains, RAG pipeline poisoning, agent identity spoofing, and MCP and A2A tool-layer exploitation.
• Lead AI red team exercises and scenario-based tabletops, delivering CVSS-scored and MITRE ATLAS-mapped findings.
• Build prompt fuzzing harnesses, guardrail regression test suites, and detection rule generators using red team TTP libraries.
• Threat-model agentic systems by mapping trust boundaries, privilege escalation paths, and blast radius across autonomous agent clusters.
• Feed red team findings into detection engineering to close security operations coverage gaps.

What You'll Have

• 4-12+ years of experience in application security, AI/ML security, or offensive security research.
• At least one demonstrable AI-specific assessment or published finding.
• Hands-on offensive experience with LLM attack surfaces, including jailbreaks, multimodal injection, agentic control gaps, and indirect prompt injection.
• Working knowledge of MLOps pipelines, ML engineering concepts, or cloud security.
• CFP submissions, responsible disclosure history, or published AI security research are strong differentiators.

What o9 Offers

• A flat organization with an entrepreneurial culture.
• The opportunity to make a difference in a scale-up environment.
• A support network and opportunities to learn from colleagues.
• An international working environment and emphasis on diversity.
• Work-life balance and opportunities for volunteering and social impact initiatives.

Hiring Process

• Candidates create a profile in Workday and participate in an initial video or phone discussion.
• The interview process includes a 60-minute technical panel, two technical discussions, and a managerial round.
• The first interview is virtual, while the second technical interview and hiring manager round are in person.