01 / THE DETAILSRole overview
Get to know the opportunity
Evaluate static-analysis tools using controlled, runnable examples of security weaknesses in AI applications.
02 / THE DETAILSWhat you’ll be doing
Your day-to-day contribution
- Create small agent or retrieval-based test repositories with vulnerable, fixed and near-miss versions.
- Trace data flows, authorisation boundaries and security controls.
- Write deterministic tests and explain findings, severity and remediation.
03 / THE DETAILSWho this could suit
See where your experience could fit
Application-security engineers with practical AI-agent or retrieval-system development experience.
04 / THE DETAILSWhat you’ll need
Experience, skills and essential requirements
- At least five years in application or product security, or security-focused software engineering, is sought.
- You need secure review, source-to-sink or taint-analysis experience, hands-on agent/RAG frameworks, production Python or TypeScript, and strong authorisation knowledge.
- Relevant security-risk frameworks and threat modelling are preferred.
You don’t have to match every requirement exactly. We welcome applicants with different backgrounds, levels of experience and transferable skills.
05 / THE DETAILSPay and working arrangements
Rates, commitment and working arrangements
Up to $150 per hour, depending on evaluation and location. Remote contractor engagement lasting up to two weeks. The commitment is at least four hours a day and 20 hours a week, with four hours overlapping Pacific time.
06 / THE DETAILSWhat happens next
How to move forward
Apply through Find Jobs in AI with your profile and CV. We’ll review your application and, if you’re a good fit, we’ll be in touch about the next steps. Later review includes an AI interview of around 25 minutes and application assessment.