AI Security Specialist
Sandeep ReddyUnited StatesMIDPosted 2h ago
AIMachine LearningGenerative AIThreat ModelingAdversarial TestingAI Red TeamingAPI SecurityIAMEncryptionLoggingAI GovernanceRisk Management
About the Role
We are looking for an experienced AI Security Specialist to join our team and help shape secure, resilient, and risk-informed AI adoption across the full model lifecycle.
Key Responsibilities
• Assess AI/ML architectures, training/inference pipelines, and LLM-enabled applications to identify and remediate security gaps.
• Perform threat modeling for predictive and generative AI (addressing prompt injection, data poisoning, evasion, privacy leakage, and model extraction).
• Lead adversarial testing, AI red teaming, and pre/post-deployment control validation.
• Define security guardrails for data/model access, API exposure, secrets management, and isolation boundaries.
• Establish monitoring and detection for anomalous model behavior, policy violations, and service abuse.
• Partner with engineering, AppSec, data science, and governance teams to embed AI security into SDLC checkpoints and align with frameworks like MITRE ATLAS and OWASP Top 10 for LLMs.
Requirements
• 3+ years of professional experience with deep knowledge of AI/ML pipelines, inference services, and application integrations.
• Hands-on experience with AI/ML threat modeling, adversarial ML concepts, and securing GenAI workflows (RAG, tool/plugin use, prompt flows).
• Strong foundation in API security, IAM, encryption, logging, and AI governance/risk management.
• Experience with AI red teaming and certifications such as CISSP, CCSP, or Cloud Security credentials.