AI Runtime Security Engineer

Salt; Polska; Remote; PLN 396,000 - 660,000; Full time

Job summary

Salt is seeking an experienced AI Runtime Security Engineer to secure GenAI platforms across a rapidly growing international organisation. The role sits at the intersection of Cyber Security, AI Engineering, MLOps and Cloud Security, focusing on protecting AI systems throughout their operational lifecycle.

You will design, implement, and monitor security controls that protect AI models, LLM applications, agentic workflows, inference environments and AI infrastructure from threats such as prompt

Qualifications

• 5+ years in cyber security, cloud security, or DevSecOps.
• Hands-on security for AI/ML/GenAI environments.
• Experience with cloud platforms (AWS/Azure/GCP) and containers.
• Knowledge of SIEM, threat detection, and incident response.

Responsibilities

• Design and implement runtime security controls for AI and GenAI apps.
• Secure LLM deployments across cloud, hybrid and on-premise environments.
• Develop monitoring to detect AI-specific threats including data leakage and jailbreaks.
• Integrate security tooling into CI/CD and MLOps pipelines.
• Collaborate with AI engineers, platform teams and security architects to secure-by-design AI solutions.
• Define logging, detection, and response processes for AI incidents.
• Perform threat modelling and security assessments of AI frameworks and APIs.

Skills

Cyber Security

AI Security

Threat Modelling

Cloud Security

CI/CD & MLOps

Tools

AWS

Azure

GCP

Kubernetes

Docker

SIEM

Security Monitoring

Job description

We are seeking an experienced AI Runtime Security Engineer to help secure next-generation AI and GenAI platforms across a rapidly growing international organisation. This role sits at the intersection of Cyber Security, AI Engineering, MLOps and Cloud Security, focusing on protecting AI systems throughout their operational lifecycle.

You will be responsible for designing, implementing, and monitoring security controls that protect AI models, LLM applications, agentic workflows, inference environments and AI infrastructure from emerging threats such as prompt injection, data poisoning, model theft, adversarial attacks, sensitive data leakage and unauthorised model access.

This is a fully remote position open to candidates located across Europe.

Key Responsibilities

• Design and implement runtime security controls for AI and GenAI applications.
• Secure Large Language Model (LLM) deployments across cloud, hybrid and on-premise environments.
• Develop monitoring capabilities to detect AI-specific threats including:
• Jailbreak attempts
• Data leakage
• Integrate AI security tooling into CI/CD and MLOps pipelines.
• Build guardrails and policy enforcement mechanisms for AI applications and autonomous agents.
• Perform threat modelling and security assessments of AI systems.
• Collaborate with AI Engineers, Data Scientists, Platform Engineers and Security Architects to implement secure-by-design AI solutions.
• Define logging, detection, and response processes for AI-related security incidents.
• Conduct security reviews of AI frameworks, APIs, vector databases and model-serving environments.
• Support compliance initiatives relating to AI governance and emerging AI regulations.
• Contribute to AI security architecture standards, best practices and security roadmaps.

Required Experience

• 5+ years of experience within Cyber Security, Cloud Security, Application Security or DevSecOps.
• Hands-on experience securing AI, Machine Learning or Generative AI environments.
• Strong understanding of AI/LLM security risks and mitigations.
• Experience with cloud platforms including AWS, Azure or Google Cloud Platform.
• Knowledge of Kubernetes, Docker and container security.
• Experience securing APIs, microservices and distributed systems.
• Familiarity with MLOps platforms and AI deployment frameworks.
• Understanding of SIEM, security monitoring, threat detection and incident response.
• Experience performing threat modelling and security assessments.

Desired Skills

• Knowledge of AI Runtime Security platforms such as:
• Microsoft Security for AI
• Protect AI
• Lakera
• HiddenLayer
• NVIDIA AI Security solutions
• Experience with LLM frameworks including LangChain, LlamaIndex, Semantic Kernel or similar.
• Familiarity with vector databases, RAG architectures, and AI agents.
• Understanding of adversarial machine learning techniques and AI attack methodologies.