AI Security Engineer – System Security

This is a fully remote position, open to applicants in Ukraine.

📋 Description

• Evaluate the AI systems and infrastructure, encompassing local and cloud LLM deployments, gateways, vector stores, and agentic/MCP components, while offering clear recommendations for necessary hardening measures and opportunities for enhancement.

• Analyze current guardrails and controls, such as input/output filtering, prompt-injection defenses, rate limiting, and authentication, against industry best practices, providing suggestions to bolster their effectiveness and spearheading the implementation of improvements and new controls to guarantee the secure and responsible application of AI.

• Provide guidance on secure-by-design AI architecture by reviewing team designs and deployments in line with recognized frameworks (OWASP, MITRE ATLAS, NIST AI RMF, ISO/IEC 42001).

• Suggest and prioritize hardening measures across the infrastructure supporting both self-hosted and cloud-based LLMs, assisting teams through the remediation process.

• Assess the AI supply chain, including model provenance, AIBOM/SBOM, dependency and artifact scanning, and offer recommendations to fill any identified gaps (Including Vibe Coded Applications).

• Establish standards, reference patterns, and best-practice guidance to ensure that teams throughout Playtech develop and manage AI securely.

• Evaluate logging, observability, and detection coverage for AI workloads mapped to frameworks such as MITRE ATLAS, and suggest improvements to ensure effective monitoring and response by the SOC across the entire AI attack surface.

• Review identity, access, and secrets management for models, tools, and data, advising on enhancements to least-privilege principles.

• Assist with compliance in a regulated environment by providing audit-ready assessments, evidence, and documentation.

• Foster innovation within the team by exploring and, where feasible, implementing Agentic AI usage within the unit to streamline time-consuming tasks (Chatbots, automation with Hermes or n8n, etc).

⛳️ Requirements

• Possess valid and relevant Certifications or equivalent, verifiable experience in Cyber Security and/or Information Technology.

• Demonstrate substantial infrastructure and security engineering experience, including Linux, networking, cloud, IAM, container security, and automation.

• Be well-versed in both self-hosted LLM deployment and cloud LLM platforms (e.g., Azure Foundry, Amazon Bedrock, Google VertexAI, Ollama, LMStudio, etc.).

• Capable of reviewing and evaluating AI systems against best practices and providing clear advice to teams on areas to harden, improve, or remediate consistently.

• Possess prior knowledge of LLM-specific threats, including prompt injection, sensitive data disclosure, data/model poisoning, excessive agency, insecure output handling, supply-chain risks, and strategies to mitigate these issues.

• Familiar with various AI security frameworks and guidelines, including OWASP Top 10 for LLM Applications (2025) and for Agentic Applications (2026), MITRE ATLAS, NIST AI RMF, ISO/IEC 42001, CISA/NSA guidance, and the EU AI Act, and able to translate them into actionable controls.

• Have previous experience in guardrail implementation and design evaluation, focusing on prompt-injection defense, output validation, and hallucination mitigation.

• Exposure to using infrastructure-as-code (Terraform, Ansible) and CI/CD pipelines to create repeatable controls.

• Experienced in navigating and working within regulated environments such as gaming, finance, or healthcare.

• Exhibit strong communication, presentation, and collaboration skills, with an emphasis on documentation and cross-team collaboration being central to this role.

🏝️ Benefits

• Collaboration across teams

• Ownership, curiosity, and a proactive approach to tackling complex security challenges

• Continuous learning and the opportunity to advance in the role while engaging with AI security topics that are increasingly significant for the business.

• Practical impact, with the opportunity to influence Playtech’s AI future and support secure AI integration throughout the company.