
Associate Director, AI Security Architect
S&P Global2 days ago
Hyderābād, IndiaStaff+
Responsibilities
- Define and operationalize an AI security strategy covering models, data pipelines, orchestration layers, agents, and integrations across AWS, Azure, GCP, OCI, and on-premises or edge environments.
- Establish and maintain an AI risk framework aligned with enterprise risk taxonomies, control objectives, regulatory requirements, NIST AI RMF, and ISO/IEC 23894.
- Create AI security policies and standards covering prompt safety, model access, agent permissions, data retention, evaluation, provenance, and watermarking.
- Lead security architecture reviews for hosted and self-hosted models, RAG systems, agents, MCP/ACP/A2A integrations, tool ecosystems, vector databases, and AI pipelines.
- Develop multi-cloud AI security reference architectures covering IAM, workload identity, secrets and key management, network segmentation, private connectivity, data security, model security, and confidential computing.
- Design and implement agent safety controls including sandboxing, least-privilege tooling, capability constraints, RBAC/ABAC, prompt-injection defenses, jailbreak mitigation, and prompt-leak protection.
- 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 observability.
- Embed security into LLMOps/MLOps CI/CD through model scanning, 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 architecture, data science, and platform teams; conduct enablement and threat-modeling workshops; and report AI security KPIs, incidents, and risk reduction to executives.
Requirements
- 10+ years of experience in information security, including 4+ years in cloud security and 2+ years in AI/ML or LLMOps security.
- Hands-on expertise with AWS, Azure, Google Cloud Platform, and Oracle Cloud Infrastructure security services and AI platforms.
- Proficiency 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, MCP, ACP, A2A, and function or tool calling.
- Experience with threat modeling and offensive testing for AI systems, including prompt injection and agent misuse.
- Strong understanding of AI privacy and compliance requirements, including GDPR, CCPA, GLBA, and sector-specific regulations.
- Preferred experience deploying secure agentic AI in production, using confidential computing and privacy-preserving ML, and implementing model risk management and AI explainability or traceability.
- Preferred background in financial services or other regulated industries, with expertise in data governance and CSPM/CNAPP for AI workloads.
- Preferred certifications include CISSP, CCSP, CISM, cloud security certifications, machine learning or AI certifications, and privacy certifications such as CIPP/E or CIPM.
Benefits
- Health care coverage and wellness benefits.
- Generous flexible paid time off.
- Continuous learning resources and professional development support.
- Retirement planning, continuing education, company-matched student loan contributions, and financial wellness programs.
- Family-oriented benefits, retail discounts, and referral incentive awards.