Staff Security Engineer - AI Enablement

Trustly•San Francisco, CA

3d•Hybrid

About The Position

Trustly is hiring a Staff AI Enablement Security Engineer to help secure its AI transformation. The role is one of two senior security individual contributors aligned to the effort, with a focus on Claude, Model Context Protocol (MCP) implementations, and broader agentic AI tooling used internally and in Trustly products. The engineer will define security standards and controls for AI systems, partner with the AI Enablement team to assess and mitigate risk, and build tooling and frameworks that support secure AI adoption. This is a hybrid role based in Trustly’s San Francisco hub, with team members expected in the office Tuesday through Thursday. Trustly describes its environment as collaborative and innovative, with colleagues across multiple regions. The company’s benefits for full-time employees include flexible paid time off and generous PTO accrual plans; medical, dental, vision, and other insurance; FSA and HSA plans; a home office setup allowance; an internet stipend; a retirement plan match for 401(k) and RRSP; and gender-neutral paid parental leave.

Requirements

At least 8 years of security engineering experience, including at least 2–3 years focused on AI/ML security, LLM security, or security for data-intensive systems.
Hands-on understanding of AI security threats, including prompt injection, jailbreaking, data poisoning, model exfiltration, insecure agentic tool use, and MCP-specific attack surfaces.
Security engineering experience in threat modeling, secure design review, penetration testing, and building security monitoring infrastructure.
Familiarity with MCP architecture, LLM orchestration frameworks, and agentic AI deployment patterns, including reasoning about security at the level of individual tool calls and context windows.
Track record of operating at Staff+ individual-contributor scope and driving security decisions across multiple teams through technical credibility and architectural influence.
Excellent communication skills, including the ability to explain emerging AI security risks to technical and non-technical audiences and build trust with engineering teams.

Responsibilities

Own security assessment and risk management for Trustly’s AI and LLM systems, including Claude, MCP server implementations, agentic workflows, and AI-assisted developer tooling.
Define and implement security controls, access governance, and monitoring frameworks for AI systems, addressing prompt injection, data leakage, model misuse, and agentic system abuse.
Partner with the AI Enablement team to embed security early in AI feature development through threat modeling, architecture reviews, and guidance on safe deployment patterns.
Build and maintain AI-specific security monitoring tools to detect anomalous model behavior, unauthorized data access, and policy violations in real time.
Develop and maintain AI security standards, guidelines, and training resources for engineering teams.
Track emerging AI security attack vectors, defensive techniques, and regulatory developments relevant to LLM and agentic system security.