Location : India(It might include travel to Johannesburg)

Work mode: Hybrid

Employment Type (FTE or Contract) : Contract

Contract Duration (if applicable) : 4-5 month

Shift Timings Johannesburg time

Only immediate joiners(No serving notice period/Bench candidates)

We are looking for a Senior Security Consultant with 10+ years of cybersecurity experience and deep, hands-on expertise in AI/ML security to join the AI CoE. This is a hybrid role: you will act as a trusted advisor to internal business leaders and external clients on AI risk, governance and secure adoption, while also rolling up your sleeves to red-team LLM applications, assess AI pipelines and define the security architecture for our AI platforms.

You will be the security voice in the room when new AI use cases are scoped, the person the delivery teams call when an agent needs to touch production data, and the expert clients trust to tell them what "secure AI" actually means in practice.

Key Responsibilities

AI Security Advisory & Client Engagement

- Serve as the lead security advisor on AI engagements for internal business units and enterprise clients, translating AI risk into clear, business-relevant recommendations for CISOs, CIOs, CDOs and product leadership.
- Define and drive the AI security strategy and roadmap for the AI CoE, aligned to enterprise security policy, regulatory obligations and business objectives.
- Lead AI risk assessments and security reviews of proposed use cases, third-party AI products, foundation-model providers and internally built AI solutions; own the go / no-go security recommendation.
- Support pre-sales and solutioning: shape AI security service offerings, contribute to proposals and RFP responses, scope engagements, estimate effort and present at client workshops and executive briefings.
- Establish and maintain the AI security governance framework policies, standards, control libraries, review gates and approval workflows mapped to NIST AI RMF, ISO/IEC 42001, ISO/IEC 27001, the EU AI Act and applicable regional regulations.
- Act as the primary security liaison between the AI CoE and Enterprise Security, Risk & Compliance, Legal, Privacy and Data Governance functions.

Hands-on AI Security Engineering & Testing

- Plan and execute AI red-teaming and adversarial testing of LLM applications, RAG pipelines, copilots and agentic systems prompt injection (direct and indirect), jailbreaks, data exfiltration, tool/function-call abuse, excessive agency, model and system-prompt extraction, and training-data poisoning.
- Perform threat modelling for AI architectures (STRIDE / MITRE ATLAS / OWASP Top 10 for LLM Applications), covering models, orchestration layers, vector stores, agent frameworks, MCP/tool integrations, plug-ins and data pipelines.




- Design and validate secure MLOps / LLMOps practices: model provenance and supply-chain integrity, model registry security, secrets and key management, secure fine-tuning and evaluation pipelines, artefact signing and SBOM/AI-BOM.
- Define and implement AI guardrails and runtime controls – input/output filtering, content moderation, PII/DLP controls, rate limiting, policy enforcement and AI firewall / gateway patterns – and integrate them with existing SOC monitoring, SIEM and incident response.
- Build and maintain automated AI security testing tooling (e.g., Garak, PyRIT, Promptfoo, custom harnesses) and integrate security evaluation into CI/CD for AI products.
- Conduct security reviews of cloud AI services and platforms (Azure OpenAI / AI Foundry, AWS Bedrock / SageMaker, Google Vertex AI, Databricks) including identity, network isolation, data residency and logging configurations.
- Lead incident response for AI-specific security events – model abuse, data leakage via AI, compromised agents – and drive root-cause analysis and remediation.

Leadership, Enablement & Thought Leadership

- Mentor and technically lead a pod of security consultants and engineers; review deliverables and uphold quality standards across AI security engagements.
- Develop and deliver AI security training and awareness programmes for developers, data scientists, product owners and executives; create secure-AI development guidelines and reference architectures.
- Contribute to thought leadership – whitepapers, conference talks, internal communities of practice and industry working groups – and keep the organisation ahead of the evolving AI threat landscape.
- Track and evaluate emerging AI security research, tools and regulation; advise on adoption and update standards accordingly.

Required Qualifications & Experience

- 10+ years of progressive experience in cybersecurity, including at least 5 years in a consulting, advisory or security-architecture capacity with direct client or senior-stakeholder exposure.
- 2–3+ years of hands-on experience securing AI/ML or generative-AI systems – LLM application security testing, AI red-teaming, ML pipeline security or AI governance implementation in a production environment.
- Robust working knowledge of OWASP Top 10 for LLM Applications, MITRE ATLAS, NIST AI RMF, ISO/IEC 42001, ISO/IEC 27001/27002 and the EU AI Act; ability to map these to practical, testable controls.




- Deep technical foundations across application security, cloud security (at least one of Azure, AWS or GCP), identity & access management, data protection, and DevSecOps.
- Practical understanding of LLM and GenAI architectures – transformers, embeddings, RAG, fine-tuning, agent frameworks (LangChain, LlamaIndex, Semantic Kernel, AutoGen), MCP and tool/function calling – and their security implications.
- Proficiency in Python and comfort reading and writing code to build test harnesses, automate assessments and review AI application code.
- Proven experience leading threat modelling, penetration testing or red-team engagements and producing executive-grade reports and remediation roadmaps.
- Excellent communication, facilitation and influencing skills – able to present complex technical risk to C-level audiences and to challenge stakeholders constructively.
- Experience working in a large, matrixed multinational environment, across time zones, cultures and regulatory jurisdictions.
- Bachelor's degree in Computer Science, Information Security, Engineering or a related field (or equivalent practical experience).

Preferred Qualifications

- Certifications such as CISSP, CCSP, OSCP, GIAC (GCPN / GWAPT / GCTI), cloud security specialty certifications, or emerging AI-focused credentials (e.g., ISO/IEC 42001 Lead Implementer/Auditor, IAPP AIGP).
- Master's degree in Cybersecurity, AI/ML, Data Science or related discipline.
- Experience with privacy-enhancing technologies (differential privacy, federated learning, confidential computing) and model-level attacks/defences (membership inference, model inversion, adversarial examples, data poisoning).
- Familiarity with AI security and governance tooling (e.g., Microsoft Purview / Defender for AI, Lakera, Protect AI, Robust Intelligence, HiddenLayer, Credo AI, IBM watsonx.governance).
- Published research, open-source contributions, CTF/red-team achievements or conference presentations in AI security.
- Experience in regulated industries such as financial services, healthcare, telecommunications or public sector.

Key Competencies

- Strategic thinking with technical depth – equally comfortable defining a multi-year AI security roadmap and demonstrating a prompt-injection exploit live.
- Risk-based judgement – balances innovation velocity against security and regulatory obligations, and knows when to say "yes, with conditions".
- Stakeholder management and executive presence – builds trust with business, technology and client leadership.
- Ownership and delivery focus – drives engagements end-to-end with high quality under tight timelines.
- Continuous learning – keeps pace with a field where the threat landscape changes monthly.

📌 Senior Security ConsultantH (India)
🏢 Tecnoprism
📍 India