Staff Security Engineer - AI Enablement - Trustly
- Work Style Hybrid
- Location San Francisco, CA
- Experience Staff
- Job Type Full-time
Job Description
Trustly is a global leader in open banking payments, enabling fast, secure account-to-account transfers and establishing Pay by Bank as a new standard at checkout for merchants and consumers worldwide.
We are hiring a Staff Security Engineer - AI Enablement for our San Francisco, CA team. This role sits within the Security function and focuses on securing Trustly's AI-native transformation - defining security standards and controls for LLMs, MCP implementations and agentic AI tooling used across engineering and product.
This is a full-time hybrid position offering competitive compensation, comprehensive benefits and the chance to work at one of the leading global open banking payment platforms.
We are hiring a Staff Security Engineer - AI Enablement for our San Francisco, CA team. This role sits within the Security function and focuses on securing Trustly's AI-native transformation - defining security standards and controls for LLMs, MCP implementations and agentic AI tooling used across engineering and product.
This is a full-time hybrid position offering competitive compensation, comprehensive benefits and the chance to work at one of the leading global open banking payment platforms.
Responsibilities
Own security assessment and risk management for Trustly's AI and LLM systems, including agentic workflows and AI-assisted developer tooling.
Define and implement security controls, access governance and monitoring frameworks for AI systems, covering prompt injection, data leakage and model misuse.
Partner with the AI Enablement team to embed security from the start of AI feature development through threat modelling and architecture review.
Build and maintain tooling for AI-specific security monitoring, detecting anomalous model behaviour and policy violations in real time.
Develop AI security standards, guidelines and training resources for engineering teams across the company.
Define and implement security controls, access governance and monitoring frameworks for AI systems, covering prompt injection, data leakage and model misuse.
Partner with the AI Enablement team to embed security from the start of AI feature development through threat modelling and architecture review.
Build and maintain tooling for AI-specific security monitoring, detecting anomalous model behaviour and policy violations in real time.
Develop AI security standards, guidelines and training resources for engineering teams across the company.
Requirements
8+ years of security engineering experience, including 2-3 years focused on AI/ML or LLM security.
Deep hands-on understanding of the AI security threat landscape: prompt injection, jailbreaking, data poisoning and insecure agentic tool use.
Strong fundamentals in threat modelling, secure design review and security monitoring infrastructure.
Familiarity with MCP architecture, LLM orchestration frameworks and agentic AI deployment patterns.
Track record of operating at Staff+ scope, driving security decisions across multiple teams through technical credibility.
Deep hands-on understanding of the AI security threat landscape: prompt injection, jailbreaking, data poisoning and insecure agentic tool use.
Strong fundamentals in threat modelling, secure design review and security monitoring infrastructure.
Familiarity with MCP architecture, LLM orchestration frameworks and agentic AI deployment patterns.
Track record of operating at Staff+ scope, driving security decisions across multiple teams through technical credibility.
Skills & Technologies
AI security
LLM
MCP
Threat modeling
Security engineering
Agentic systems
more roles
More roles at Trustly
Lisbon
New York, NY
San Francisco, CA