AI Security Engineer

At Accenture Newra AI Hub, we are not just building technology, we are redefining how banking operates. As part of our strategic collaboration with Piraeus, Newra is designed to responsibly embed AI at the core of its business, moving beyond experimentation to real-world impact at scale.

• Build AI security patterns and control requirements that help teams design, build, deploy, and monitor AI systems securely and consistently
• Create threat models for GenAI, agentic AI, machine learning, RAG, model endpoints, data pipelines, and third-party AI platforms
• Define guardrail and runtime-defense specifications embedded into AI products — input/output filtering, prompt-injection detection, data-leakage prevention, jailbreak resistance, and least-privilege boundaries for agent tool use
• Develop AI security testing approach covering adversarial prompts, abuse cases, data exposure, insecure integrations, model/tool misuse, and pre-deployment security gates
• Embed secure architecture checkpoints into product, data, engineering, cloud, security, compliance, and release processes
• Implement monitoring and response mechanisms for AI security events, including suspicious prompts, policy violations, sensitive-data exposure, tool misuse, and anomalous model behavior
• Maintain documentation and evidence for AI security posture, risk acceptance, control effectiveness, and regulatory/model compliance
• Create enablement content that helps teams understand AI threats, apply guardrails, and build secure AI products from day one

• Degree in Cybersecurity, Computer Science, Software Engineering, Data, AI/ML, Risk
• 4-5 years of experience in application security, cloud security, AI/ML engineering, DevSecOps, technology risk, or security engineering
• Working knowledge of AI/ML and GenAI architecture, including RAG, prompt flows, embeddings, vector databases, APIs, model endpoints, and agent/tool use
• Understanding of AI security risks: prompt injection, data leakage, model misuse, insecure plugins/tools, excessive agency, supply-chain risk, and model/prompt exfiltration
• Ability to perform AI threat modeling, define security requirements, and translate findings into practical engineering mitigations
• Experience with secure SDLC, vulnerability management, security testing, logging/monitoring, IAM, secrets management, and cloud security controls
• Ability to partner with product, engineering, data science, cloud, security operations, legal, risk, compliance, and Responsible AI teams
• Clear communicator, able to explain AI security risks, attack paths, controls, and residual risk

• Exposure to LLM red teaming, adversarial testing, guardrail evaluation, or runtime AI safety/security controls
• Background in banking, regulated technology environments, DORA, EU AI Act, ISO, NIST, model-risk governance

• Competitive salary and benefits, including but not limited to: life/health insurance, performance based bonuses, monthly vouchers, company car (depending on management level), flexible work arrangements, employee share purchase plan, parental leave and various corporate discounts
• Continuous training & development through global platforms & local academy
• Career coaching and mentorship to help you manage your career and develop professionally
• Ongoing strength and skill-based evaluation process
• Various opportunities to develop your career across a spectrum of clients, industries and projects
• Diverse and inclusive culture
• Opportunities to get involved in corporate citizenship initiatives, from volunteering to doing charity work
• Under our Brain Regain initiative, extra relocation benefits may apply