AI Security Engineer / Architect
o9 Solutions1 hour ago
Bengaluru, IndiaSenior
Responsibilities
- Design and execute AI-specific VAPT engagements covering prompt injection chains, RAG pipeline poisoning, agent identity spoofing, and MCP/A2A tool-layer exploitation.
- Lead AI red-team exercises and scenario-based tabletops, producing CVSS-scored and MITRE ATLAS-mapped findings with remediation guidance.
- Build and maintain AI security automation, including prompt-fuzzing harnesses, guardrail regression suites, and detection-rule generators.
- 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 improve SOC coverage across customer environments.
Requirements
- Require 4–12+ years of experience in application security, AI/ML security, or offensive security research.
- Require at least one demonstrable AI-specific security assessment or published finding.
- Require hands-on offensive experience with LLM attack surfaces, including jailbreaks, multimodal injection, agentic control gaps, and indirect prompt injection.
- Require working knowledge of MLOps pipelines, ML engineering concepts, or cloud security.
- CFP submissions, responsible-disclosure history, or published AI security research are strong differentiators.
Benefits
- Bangalore-based hybrid work arrangement.
- Flat, entrepreneurial organization with limited corporate hierarchy and opportunities to make an impact in a scale-up environment.
- Supportive team environment with ongoing learning opportunities.
- International and diverse working environment with volunteering, social-impact initiatives, and cultural celebrations.
- Interview process includes a virtual technical round, an in-person technical round, and an in-person managerial round.
Tech Stack
Categories