Staff AI Security Engineer – Enablement & Guardrails

Trustly; San Francisco (CA); Hybrid; USD 226,000 - 340,000; Full time

Benefits offered by this job

Flexible paid time off

Comprehensive medical, dental, vision

FSA & HSA plans

Home office setup allowance

Internet stipend

401k match

Parental leave

Job summary

Trustly in San Francisco is seeking a Staff AI Enablement Security Engineer to join the Security & IT team. You will secure Claude, MCP implementations, and the broader agentic AI tooling used across Trustly’s products, defining security standards and controls for AI systems while enabling fast, safe AI-enabled delivery.

You’ll partner with the AI Enablement team to model threats, review architectures, and build tooling for real-time security monitoring.

Qualifications

• 8+ years of security engineering experience with 2–3 years focused on AI/ML security, LLM security, or data-intensive systems.
• Deep understanding of AI security threat landscapes incl. prompt injection, data poisoning, model exfiltration.
• Strong fundamentals: threat modeling, secure design reviews, pentesting, security monitoring.
• Familiarity with MCP architecture, LLM orchestration, and agentic AI deployment patterns.
• Track record at Staff+ IC scope influencing architecture through credibility.
• Excellent communicator able to explain AI security risks to technical and non-technical audiences.

Responsibilities

• Own security assessment and risk management for Trustly's AI/LLM systems and agentic tooling.
• Define and implement security controls, access governance, and monitoring for AI systems.
• Partner with AI Enablement team to embed security from the start of AI feature development.
• Build and maintain tooling for AI-specific security monitoring in real time.
• Develop AI security standards, guidelines, and training resources for engineering teams.
• Stay ahead of AI security research, tracking new attack vectors and regulatory developments.

Skills

AI/ML security

Security engineering

Threat modeling

Penetration testing

Monitoring infrastructure

Staff+ IC scope

Tools

MCP (Model Context Protocol)

LLM orchestration frameworks

Agentic AI deployment patterns

Job description

Trustly in San Francisco is seeking a Staff AI Enablement Security Engineer to join the Security & IT team. You will secure Claude, MCP implementations, and the broader agentic AI tooling used across Trustly’s products, defining security standards and controls for AI systems while enabling fast, safe AI-enabled delivery.

You’ll partner with the AI Enablement team to model threats, review architectures, and build tooling for real-time security monitoring.