Security Architect
Project Role : Security Architect
Project Role Description : Define the cloud security framework and architecture, ensuring it meets the business requirements and performance goals. Document the implementation of the cloud security controls and transition to cloud security-managed operations.
Must have skills : Secure AI
Good to have skills : NA
Minimum 7.5 year(s) of experience is required
Educational Qualification : 15 years full time education
Summary:
Seeking a forward-thinking professional with an AI-first mindset to design, develop, and deploy enterprise-grade solutions using Generative and Agentic AI frameworks that drive innovation, efficiency, and business transformation.AI Red Team Lead with 9+ years of experience in red teaming, penetration testing, adversarial security testing, application security, or AI security, driving advanced adversarial testing, security assurance, and validation for GenAI, LLM applications, AI agents, and ML-powered systems across the organization. Combines deep hands-on adversarial testing capability with technical leadership, focusing on identifying systemic AI security risks, defining red team strategy, validating protections at scale, and enabling secure adoption of AI capabilities in production environments.Lead enterprise-wide AI red teaming initiatives, establish reusable attack frameworks, guide threat-led security assessments, and ensure that AI systems are tested not only for technical vulnerabilities, but also for Responsible AI risks such as fairness, explainability, safety, and governance effectiveness.
Roles & Responsibilities
Lead AI-driven solution design and delivery by applying GenAI and Agentic AI to address complex business challenges, automate processes, and integrate intelligent insights into enterprise workflows for measurable impact.
Lead and oversee AI red teaming activities across GenAI, LLM-based, agentic, and ML-powered applications, ensuring coverage of high-risk use cases, critical workflows, and business-sensitive AI deployments.
Execute and supervise advanced adversarial testing across LLMs, GenAI applications, RAG pipelines, multi-agent systems, and AI-enabled workflows.
Define enterprise-wide AI red teaming strategy, reusable adversarial test frameworks, attack libraries, and standardized testing methodologies for AI security assessments.
Establish automated red teaming pipelines and continuous security validation approaches to improve repeatability, coverage, and early detection of AI security weaknesses.
Define and guide advanced testing scenarios for prompt injection, indirect prompt injection, jailbreaks, unsafe completion generation, data leakage, model misuse, and policy evasion.
Perform and review security assessments of RAG architectures, complex prompt chains, long-context interactions, and multi-step AI workflows to identify systemic abuse paths.
Assess agentic systems for excessive permissions, unsafe autonomy, unauthorized actions, cross-tool abuse, insecure function calling, and sensitive data exposure risks.
Simulate cross-agent and prompt-chaining attacks across multi-stage workflows to validate trust boundaries, execution controls, and action governance.
Test long-term memory risks in AI agents, including memory poisoning, context manipulation, persistence abuse, and unsafe retention of sensitive information.
Evaluate design and effectiveness of input and output guardrails, policy enforcement, grounding mechanisms, content filtering, and sensitive data protection controls.
Evaluate model alignment and safety boundaries by testing misuse scenarios, harmful output generation, boundary bypasses, and unsafe model behavior under adversarial conditions.
Drive Responsible AI validation at scale, including fairness, explainability, robustness, and safety testing governance for enterprise AI use cases.
Lead AI threat modeling exercises using STRIDE adapted for AI systems and map attack scenarios to MITRE ATLAS techniques and OWASP LLM Top 10 risks.
Provide technical direction for API-level testing of AI platforms, model endpoints, integration layers, gateways, plugins, tools, and vector database interfaces.
Review and validate red team findings for technical accuracy, exploitability, business impact, and remediation readiness.
Partner with architecture, engineering, platform, product, and security teams to influence secure-by-design decisions for AI systems.
Define enterprise-wide AI red teaming strategy, attack libraries, and reusable adversarial test frameworks
Establish automated red teaming pipelines and continuous security validation approaches for AI systems
Lead AI threat modeling exercises incorporating STRIDE (adapted for AI) and MITRE ATLAS techniques
Drive Responsible AI validation at scale, including fairness, explainability, and safety testing governance
Define KPIs such as coverage across AI systems, detection vs bypass trends, and remediation effectiveness
Drive remediation validation strategy, risk acceptance discussions, and residual risk sign-off for AI deployments and control gaps.
Define and track AI red teaming KPIs such as coverage across AI systems, attack success rate, bypass trends, remediation effectiveness, and control validation outcomes.
Establish repeatable test repositories, reusable attack scenarios, evidence standards, and reporting practices for AI security validation.
Mentor team members, conduct technical reviews, and raise the overall maturity of AI red team capabilities across the organization.
Professional & Technical Skills
Strong grasp of Generative and Agentic AI, prompt engineering, and AI evaluation frameworks. Ability to align AI capabilities with business objectives while ensuring scalability, responsible use, and tangible value realization. The candidate should be AI Native.
Strong background in red teaming, penetration testing, adversarial security testing, or advanced application security, with leadership experience in complex security assessments.
Deep understanding of LLM, Agentic AI, GenAI, and ML architectures, including model lifecycles, inference flows, fine-tuning, embeddings, orchestration patterns, and RAG systems.
Strong expertise in identifying and assessing GenAI-specific threat patterns such as prompt injection, indirect injection, jailbreaks, hallucination abuse, model manipulation, data exfiltration, unsafe tool use, and unauthorized inference access.
Ability to technically evaluate GenAI and LLM systems for privacy leakage, unsafe or non-compliant outputs, fairness and bias risks, transparency gaps, explainability issues, and safety or robustness failures under adversarial conditions.
Experience designing and evaluating controls across the AI lifecycle, including design, orchestration, inference, deployment, monitoring, integrations, and third-party dependencies.
Working knowledge of Responsible AI testing approaches, including fairness assessment, subgroup analysis, explainability validation, and safety control testing.
Familiarity with explainability and interpretability concepts and tools such as SHAP, LIME, or equivalent model analysis techniques.
Experience establishing reusable attack libraries, adversarial test frameworks, and continuous validation approaches for AI systems.
Strong understanding of AI ecosystem risks, including vector databases, insecure retrieval pipelines, prompt-chain abuse, model-to-tool trust boundaries, and AI supply chain dependencies.
Hands-on familiarity with AI security and red teaming tools such as Garak, Giskard, Promptfoo, Counterfit, DeepEval, or similar adversarial testing frameworks is preferred.
Strong written and verbal communication skills, with the ability to explain technical findings, business impact, and remediation guidance to both technical and non-technical stakeholders.
Preferred certifications: OffSec AI-300 (OSAI+), AI Red Teaming Professional (AIRTP+), HTB Certified Offensive AI Expert (COAE), OSCP, CRTP & CISSP.
Additional Information
9+ years of relevant experience in security testing, red teaming, AI security, application security, or adversarial validation.
Employment Type: Full Time
This position is based in India, with location aligned to business needs.
A 15-year full-time education is required. AI Powered Tech Talent
15 years full time education
Project Role Description : Define the cloud security framework and architecture, ensuring it meets the business requirements and performance goals. Document the implementation of the cloud security controls and transition to cloud security-managed operations.
Must have skills : Secure AI
Good to have skills : NA
Minimum 7.5 year(s) of experience is required
Educational Qualification : 15 years full time education
Summary:
Seeking a forward-thinking professional with an AI-first mindset to design, develop, and deploy enterprise-grade solutions using Generative and Agentic AI frameworks that drive innovation, efficiency, and business transformation.AI Red Team Lead with 9+ years of experience in red teaming, penetration testing, adversarial security testing, application security, or AI security, driving advanced adversarial testing, security assurance, and validation for GenAI, LLM applications, AI agents, and ML-powered systems across the organization. Combines deep hands-on adversarial testing capability with technical leadership, focusing on identifying systemic AI security risks, defining red team strategy, validating protections at scale, and enabling secure adoption of AI capabilities in production environments.Lead enterprise-wide AI red teaming initiatives, establish reusable attack frameworks, guide threat-led security assessments, and ensure that AI systems are tested not only for technical vulnerabilities, but also for Responsible AI risks such as fairness, explainability, safety, and governance effectiveness.
Roles & Responsibilities
Lead AI-driven solution design and delivery by applying GenAI and Agentic AI to address complex business challenges, automate processes, and integrate intelligent insights into enterprise workflows for measurable impact.
Lead and oversee AI red teaming activities across GenAI, LLM-based, agentic, and ML-powered applications, ensuring coverage of high-risk use cases, critical workflows, and business-sensitive AI deployments.
Execute and supervise advanced adversarial testing across LLMs, GenAI applications, RAG pipelines, multi-agent systems, and AI-enabled workflows.
Define enterprise-wide AI red teaming strategy, reusable adversarial test frameworks, attack libraries, and standardized testing methodologies for AI security assessments.
Establish automated red teaming pipelines and continuous security validation approaches to improve repeatability, coverage, and early detection of AI security weaknesses.
Define and guide advanced testing scenarios for prompt injection, indirect prompt injection, jailbreaks, unsafe completion generation, data leakage, model misuse, and policy evasion.
Perform and review security assessments of RAG architectures, complex prompt chains, long-context interactions, and multi-step AI workflows to identify systemic abuse paths.
Assess agentic systems for excessive permissions, unsafe autonomy, unauthorized actions, cross-tool abuse, insecure function calling, and sensitive data exposure risks.
Simulate cross-agent and prompt-chaining attacks across multi-stage workflows to validate trust boundaries, execution controls, and action governance.
Test long-term memory risks in AI agents, including memory poisoning, context manipulation, persistence abuse, and unsafe retention of sensitive information.
Evaluate design and effectiveness of input and output guardrails, policy enforcement, grounding mechanisms, content filtering, and sensitive data protection controls.
Evaluate model alignment and safety boundaries by testing misuse scenarios, harmful output generation, boundary bypasses, and unsafe model behavior under adversarial conditions.
Drive Responsible AI validation at scale, including fairness, explainability, robustness, and safety testing governance for enterprise AI use cases.
Lead AI threat modeling exercises using STRIDE adapted for AI systems and map attack scenarios to MITRE ATLAS techniques and OWASP LLM Top 10 risks.
Provide technical direction for API-level testing of AI platforms, model endpoints, integration layers, gateways, plugins, tools, and vector database interfaces.
Review and validate red team findings for technical accuracy, exploitability, business impact, and remediation readiness.
Partner with architecture, engineering, platform, product, and security teams to influence secure-by-design decisions for AI systems.
Define enterprise-wide AI red teaming strategy, attack libraries, and reusable adversarial test frameworks
Establish automated red teaming pipelines and continuous security validation approaches for AI systems
Lead AI threat modeling exercises incorporating STRIDE (adapted for AI) and MITRE ATLAS techniques
Drive Responsible AI validation at scale, including fairness, explainability, and safety testing governance
Define KPIs such as coverage across AI systems, detection vs bypass trends, and remediation effectiveness
Drive remediation validation strategy, risk acceptance discussions, and residual risk sign-off for AI deployments and control gaps.
Define and track AI red teaming KPIs such as coverage across AI systems, attack success rate, bypass trends, remediation effectiveness, and control validation outcomes.
Establish repeatable test repositories, reusable attack scenarios, evidence standards, and reporting practices for AI security validation.
Mentor team members, conduct technical reviews, and raise the overall maturity of AI red team capabilities across the organization.
Professional & Technical Skills
Strong grasp of Generative and Agentic AI, prompt engineering, and AI evaluation frameworks. Ability to align AI capabilities with business objectives while ensuring scalability, responsible use, and tangible value realization. The candidate should be AI Native.
Strong background in red teaming, penetration testing, adversarial security testing, or advanced application security, with leadership experience in complex security assessments.
Deep understanding of LLM, Agentic AI, GenAI, and ML architectures, including model lifecycles, inference flows, fine-tuning, embeddings, orchestration patterns, and RAG systems.
Strong expertise in identifying and assessing GenAI-specific threat patterns such as prompt injection, indirect injection, jailbreaks, hallucination abuse, model manipulation, data exfiltration, unsafe tool use, and unauthorized inference access.
Ability to technically evaluate GenAI and LLM systems for privacy leakage, unsafe or non-compliant outputs, fairness and bias risks, transparency gaps, explainability issues, and safety or robustness failures under adversarial conditions.
Experience designing and evaluating controls across the AI lifecycle, including design, orchestration, inference, deployment, monitoring, integrations, and third-party dependencies.
Working knowledge of Responsible AI testing approaches, including fairness assessment, subgroup analysis, explainability validation, and safety control testing.
Familiarity with explainability and interpretability concepts and tools such as SHAP, LIME, or equivalent model analysis techniques.
Experience establishing reusable attack libraries, adversarial test frameworks, and continuous validation approaches for AI systems.
Strong understanding of AI ecosystem risks, including vector databases, insecure retrieval pipelines, prompt-chain abuse, model-to-tool trust boundaries, and AI supply chain dependencies.
Hands-on familiarity with AI security and red teaming tools such as Garak, Giskard, Promptfoo, Counterfit, DeepEval, or similar adversarial testing frameworks is preferred.
Strong written and verbal communication skills, with the ability to explain technical findings, business impact, and remediation guidance to both technical and non-technical stakeholders.
Preferred certifications: OffSec AI-300 (OSAI+), AI Red Teaming Professional (AIRTP+), HTB Certified Offensive AI Expert (COAE), OSCP, CRTP & CISSP.
Additional Information
9+ years of relevant experience in security testing, red teaming, AI security, application security, or adversarial validation.
Employment Type: Full Time
This position is based in India, with location aligned to business needs.
A 15-year full-time education is required. AI Powered Tech Talent
15 years full time education
About Accenture
Accenture is a leading global professional services company that helps the world’s leading businesses, governments and other organizations build their digital core, optimize their operations, accelerate revenue growth and enhance citizen services—creating tangible value at speed and scale. We are a talent- and innovation-led company with approximately 791,000 people serving clients in more than 120 countries. Technology is at the core of change today, and we are one of the world’s leaders in helping drive that change, with strong ecosystem relationships. We combine our strength in technology and leadership in cloud, data and AI with unmatched industry experience, functional expertise and global delivery capability. Our broad range of services, solutions and assets across Strategy & Consulting, Technology, Operations, Industry X and Song, together with our culture of shared success and commitment to creating 360° value, enable us to help our clients reinvent and build trusted, lasting relationships. We measure our success by the 360° value we create for our clients, each other, our shareholders, partners and communities.Visit us at www.accenture.com
Equal Employment Opportunity Statement
We believe that no one should be discriminated against because of their differences. All employment decisions shall be made without regard to age, race, creed, color, religion, sex, national origin, ancestry, disability status, military veteran status, sexual orientation, gender identity or expression, genetic information, marital status, citizenship status or any other basis as protected by applicable law. Our rich diversity makes us more innovative, more competitive, and more creative, which helps us better serve our clients and our communities.
Security pay context
Based on 1,675 disclosed Security salaries on RoleSuite, the role pays a median of $142K/year, with most offers between $113K and $183K (10th–90th percentile: $91K–$216K).
See the full Security salary breakdown →