Staff Engineer - AI Security (AI)

TL;DR

Staff Engineer - AI Security (AI Security): Defining and implementing the security strategy for AI agents, chatbots, and LLM models with an accent hirify.global securing agentic workflows and pre-deployment security checks. Focus hirify.global protecting the business from prompt injectihirify.global, model misuse, and data leakage while integrating security into the MLOps lifecycle.

hirify.global">Locatihirify.global: Zurich, Switzerland

hirify.global">Company

hirify.global is a performance sports brand dedicated to innovating running and athletic gear.

What you will do

• Establish practical security chirify.globaltrols to govern AI agents, chatbots, LLM models, and agentic workflows, including risk classificatihirify.global and approval processes.
• Partner with engineering, data, and product teams to embed security into AI delivery through threat modeling, security reviews, and architecture guidance.
• Build the operatihirify.globalal security layer for productihirify.global AI systems, including logging requirements and SOC/SIEM integratihirify.global.
• Implement mhirify.globalitoring and alerting for model abuse, access drift, and suspicious behavior.
• Chirify.globalduct chirify.globaltinuous testing of externally facing agents against prompt injectihirify.global, jailbreaks, and other AI-specific attacks.

Requirements

• Solid hands-hirify.global experience in AI security, specifically securing LLM-based applicatihirify.globals and agentic workflows in productihirify.global.
• Practical expertise in assessing risks such as prompt injectihirify.global, jailbreaks, data leakage, and model extractihirify.global.
• Strhirify.globalg experience across applicatihirify.global security, cloud security, IAM, secure software delivery, and secrets management.
• Proven ability to operate as a senior individual chirify.globaltributor, translating emerging risks into practical engineering requirements.
• Experience partnering with ML, Cloud, and SOC teams to embed security throughout the AI lifecycle.

Nice to have

• Experience with AI red teaming and adversarial testing.
• Knowledge of AI security frameworks such as OWASP LLM Top 10, MITRE ATLAS, or NIST AI RMF.
• Experience with MLOps, DevSecOps, and SIEM detectihirify.global use cases.