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 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 Specialist with 6–9 years of hands-on experience on adversarial testing of GenAI, LLM Application, AI agents and ML powered applications to identify real world abuse scenarios, data leakage risks, and control gaps. The role focuses on executing repeatable red team tests, validating guardrails, collecting technical evidence, and supporting remediation validation for production bound AI use cases.
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.
Execute hands on adversarial testing of LLM based applications, including prompt injection, indirect prompt injection, and jailbreak scenarios.
Perform security testing of RAG pipelines, prompt chains, and AI driven workflows to identify data leakage and unsafe output risks.
Test agentic workflows for excessive permissions, unsafe tool usage, unauthorized actions, and inappropriate data access.
Evaluate input/output guardrails such as content filtering, policy enforcement, grounding, and sensitive data masking
Conduct API level testing of AI services and supporting components including gateways, tools/plugins, and vector database endpoints
Perform adversarial testing for multimodal models (e.g., image/audio prompt injection where applicable).
Simulate cross-agent and prompt-chaining attacks across multi-step workflows.
Test long-term memory risks in agents (memory poisoning, context manipulation, persistence attacks).
Evaluate model alignment and safety boundaries (policy evasion, harmful output generation, misuse scenarios).
Reproduce issues consistently, collect technical evidence, and document practical, remediation ready findings
Support remediation validation by retesting fixes and confirming control effectiveness and residual risk
Contribute test cases, scripts, and repeatable scenarios to improve coverage and consistency of AI red team testing
Collaborate with application, platform, and security teams to explain findings and validate mitigations
Map attack scenarios to frameworks such as MITRE ATLAS and maintain traceability to OWASP LLM Top 10 risks
Evaluate risks related to training data exposure, embedding leakage, insecure retrieval behavior, and unauthorized knowledge access
Identify weaknesses in model-to-tool trust boundaries, including insecure function calling, unsafe parameter passing, and tool output manipulation
Track and report testing metrics such as attack success rate, guardrail bypass rate, and coverage across AI systems

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.
Hands on experience in red teaming, penetration testing, or vulnerability validation for applications or cloud services
Experience with OWASP LLM Top 10, MITRE ATLAS, and other AI security testing frameworks and attack taxonomies
Good understanding of LLM and GenAI architectures including transformers, embeddings, fine tuning, inference flows, and RAG
Hands on expertise in adversarial Responsible AI testing of GenAI/LLM systems, including detection of privacy and training data leakage, policy violating or unsafe outputs, transparency and explainability gaps, and robustness or safety failures under adversarial inputs
Experience with fairness and bias testing techniques (e.g., subgroup analysis, disparate impact evaluation)
Familiarity with explainability tools such as SHAP, LIME, or equivalent model interpretability approaches
Experience testing GenAI specific risks such as prompt injection, hallucination abuse, data leakage, model misuse, and unauthorized access
Strong Python scripting skills for PoC development, automation, and API testing
Experience with AI security/red teaming tools such as Garak, Giskard, Promptfoo, Counterfit, DeepEval, or similar frameworks
Familiarity with LLM deployment models (hosted APIs, self hosted models) and associated threat surfaces
Ability to analyze prompts, inference responses, logs, and API behavior to identify anomalous or risky patterns
Clear documentation skills with ability to convert technical findings into actionable remediation guidance
Preferred certifications: AI Red Teaming Professional (AIRTP+), HTB Certified Offensive AI Expert (COAE), OSCP, CRTP & CISSP.

Additional Information:
6 to 9 years of relevant experience in security testing, AI red teaming, or application security
Employment Type: Full Time
This position is based all over India, based upon business requirements.
A 15 year full time education is required AI Powered Tech Talent15 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 atwww.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, militaryveteran status, sexual orientation, gender identity or expression, genetic information, marital status, citizenship status or any other basis as protected by applicablelaw. Our rich diversity makes us more innovative, more competitive, and more creative, which helps us better serve our clients and our communities.