Key Responsibilities

- Lead client engagements focused on securing AI, GenAI, and ML workloads across AWS, Microsoft Azure, and Google Cloud.

- Design and implement AI security strategies, architectures, governance models, and control frameworks aligned with business and regulatory requirements.

- Conduct AI security assessments across cloud-hosted AI/ML and GenAI environments.

- Evaluate controls against NIST CSF, CSA CCM, ISO 27001, NIST AI RMF, ISO 42001, and related frameworks.

- Lead threat modelling and architecture reviews for AI and GenAI solutions.

- Assess risks including prompt injection, jailbreaks, insecure output handling, excessive agent permissions, sensitive data exposure, model misuse, and insecure tool integrations.

- Define secure reference architectures for model endpoints, APIs, RAG pipelines, vector stores, plugins, agent frameworks, orchestration layers, and external integrations.

- Guide secure deployment of Amazon Bedrock, SageMaker, Azure AI Foundry, Azure OpenAI, Azure Machine Learning, and Google Vertex AI.

- Implement controls around private connectivity, encryption, key management, secrets management, access restriction, tenant isolation, content safety, logging, and monitoring.

- Integrate security into MLOps, and MLSecOps pipelines.

- Embed policy validation, secrets handling, model governance, and compliance checks into CI/CD and ML workflows.

- Define controls across the full AI lifecycle, including data ingestion, training, validation, deployment, runtime monitoring, incident response, drift review, and retraining.

- Lead AI governance activities covering model inventory, risk classification, approval workflows, traceability,



control mapping, audit readiness, and policy alignment.

- Drive AI security posture management using CNAPP, CSPM, CWPP, DSPM, SIEM, and cloud-native security tools.

- Oversee monitoring and incident response for suspicious prompt activity, agent misuse, unauthorized model access, data leakage, and control failures.

- Lead AI security testing including misuse-case testing, prompt attack validation, model guardrail reviews, red-team support, and remediation planning.

- Manage stakeholders across Security, Cloud, DevOps, Architecture, Data, ML Engineering, Privacy, Legal, and Risk teams.

- Contribute to proposals, solutioning, thought leadership, reusable assets, and cloud AI security practice development.

Ideal Candidate

- Experience in cloud security, cybersecurity consulting, cloud engineering, AI security, or related disciplines.

- Proven experience on security, cloud, or AI projects.

- Strong experience designing, assessing, or implementing controls for cloud-hosted applications and AI/ML platforms.

- Deep understanding of AWS, Azure, and Google Cloud security.

- Strong knowledge of AI/ML and GenAI risks including prompt injection, model misuse, data leakage, agent security, and responsible AI.

- Hands-on experience with IAM, network security, encryption, key management, secrets management, logging, monitoring, and policy enforcement..

- Familiarity with Amazon Bedrock, SageMaker, Azure AI Foundry, Azure ML, Azure OpenAI, Anthropic, Mythos, and Vertex AI.

- Strong knowledge of NIST AI RMF, ISO 42001

- Robust communication skills and ability to explain technical and risk matters to senior and non-technical stakeholders.

📌 Manager/Lead - AI Cyber Security (Navi Mumbai)
🏢 ICICI Securities
📍 Navi Mumbai