Harshit Srivastava AISPM(WIZ, Accuknox, Cortex Cloud)
Experience: AI Security / ML Security / AI Red Teaming / AI Governance / AI Risk Management
Skills Required -
1. Design and implement end?to?end security controls across AI/ML lifecycle (data ingestion ? model training ? deployment ? inference)
2. Establish AI?specific threat models (prompt?level, model extraction, data poisoning, membership inference, jailbreaks)
3. Conduct risk assessments for AI models, LLM integrations, vector databases, and AI agents.
4. Deploy and manage AISPM solutions to continuously evaluate AI system posture
5.Implement runtime anomaly detection for model misuse, prompt?based attacks, and abnormal inference traffic.
6. Integrating AI access with cloud native IAM solutions
7. Apply controls for input/output validation, injection protection, and adversarial robustnessn
8.Conduct continuous AI red?team operations targeting Prompt injection,



Jailbreaking & output manipulation, Data exfiltration through LLM responses, Model extraction & shadow models, Adversarial sample crafting
Responsibility –
1. Implementing Prisma AI security solutions and providing end-to-end support to clients
2. Define and maintain the security architecture for AI/ML platforms, pipelines, and model?serving environments
3. Establish and enforce AI secure?development and deployment standards across data science, engineering, and application teams.
4.Collaborate with enterprise security, cloud security, compliance, legal, and privacy teams to ensure responsible AI governance. AI Red Teaming ( Prisma AIRS) AI Access (Prisma Access Browser, Google Enterprise Browser) AI Runtime Security

📌 AI Security (8374,1113,1125) (India)
🏢 We Search
📍 India