
Associate Director, AI Security Architect
S&P Global2 days ago
Noida, India +2 moreStaff+
Responsibilities
- Define and operationalize enterprise AI security strategy across models, data pipelines, orchestration layers, agents, integrations, and multi-cloud environments.
- Own the AI Risk Framework and map AI security controls to enterprise risk taxonomies, regulatory requirements, and standards.
- Create AI security policies and standards covering prompt safety, model access, agent permissions, data retention, evaluation, provenance, and watermarking.
- Perform security architecture reviews for hosted and self-hosted models, RAG systems, agents, MCP/ACP/A2A integrations, pipelines, vector databases, and observability systems.
- Develop and maintain secure reference architectures for identity, network segmentation, data security, model security, confidential computing, and secure enclaves.
- Design and implement agent safety controls including sandboxing, least-privilege tooling, capability constraints, policy enforcement, prompt-injection defenses, jailbreak mitigation, and prompt-leak prevention.
- Build secure AI agents and MCP/ACP/A2A integrations with runtime isolation, egress controls, command filtering, audit trails, content filters, output validation, semantic gateways, and telemetry.
- Embed LLMOps/MLOps security into CI/CD through model artifact scanning, dependency SBOMs, policy-as-code, attestation, and controlled environment promotion.
- Implement continuous AI evaluation covering adversarial prompts, scenario testing, safety and accuracy metrics, drift, hallucinations, bias, and fairness.
- Partner with cloud architecture, data science, and cloud platform teams to deliver secure AI capabilities.
- Educate engineering teams through playbooks, secure coding guidance, prompt hygiene, model evaluation standards, and threat-modeling workshops.
- Report AI security KPIs, incidents, risk reduction, and executive-level risk/value trade-offs.
Requirements
- 10+ years of information security experience, including 4+ years in cloud security and 2+ years in AI/ML or LLMOps security.
- Hands-on multi-cloud experience with AWS, Azure, Google Cloud Platform, and Oracle Cloud Infrastructure.
- Experience with AWS IAM, KMS, PrivateLink, Bedrock, SageMaker, GuardDuty, and CloudTrail.
- Experience with Azure Entra ID, Key Vault, Private Endpoints, Azure OpenAI, Azure ML, and Defender for Cloud.
- Experience with GCP IAM, KMS, VPC Service Controls, Vertex AI, Cloud Armor, and Audit Logs.
- Experience with OCI IAM, Vault, Service Gateway, Data Science, and Logging & Events.
- Security engineering expertise in Zero Trust, policy-as-code, secrets management, container security, SBOMs, SLSA, and Sigstore.
- Knowledge of RAG, vector databases, prompt engineering, AI guardrails, evaluation frameworks, agent orchestration, and function/tool calling.
- Experience with threat modeling and offensive testing for AI systems, including prompt injection and agent misuse.
- Strong understanding of privacy and compliance requirements affecting AI, including GDPR, CCPA, GLBA, and sector-specific regulations.
- Preferred experience deploying agentic AI in production with secure toolchains and runtime isolation.
- Preferred familiarity with AMD SEV, Intel SGX, Azure Confidential Computing, Nitro Enclaves, differential privacy, federated learning, and homomorphic encryption.
- Preferred experience with model risk management, AI explainability, traceability, provenance, watermarking, evaluation pipelines, data governance, CSPM, and CNAPP.
- Background in financial services or another highly regulated industry is preferred.
- CISSP, CCSP, CISM, cloud security certifications, machine learning or AI certifications, and privacy certifications such as CIPP/E or CIPM are preferred.
Benefits
- Health care coverage and wellness benefits.
- Generous paid time off and flexible downtime.
- Continuous learning resources and career development support.
- Retirement planning, continuing education, company-matched student loan contributions, and financial wellness programs.
- Family-oriented benefits, retail discounts, and referral incentive awards.
- Benefits vary by country; the listed location is Hyderabad, Telangana, India.