GenAI Security Evaluation Engineer
- Pay
- Up to $150/hour
- Where
- Remote
- Type
- Contract
- Eligibility
- Country eligibility not stated. Check with the provider before applying.
- Listing
- Last verified Oct 7, 2026
Apply opens the provider’s application page. You apply there yourself: we never submit applications, and opening the page doesn’t mean you’ve applied. Nobody can promise you’ll be hired.
Some Apply links are referral links. If you apply through them, the provider may pay us a commission. Referral disclosure
About the role
Evaluate how effectively static analysis tools detect vulnerabilities in GenAI applications. Build small, runnable agent and RAG codebases containing realistic Sensitive Information Disclosure and Excessive Agency examples across tool calling, memory and MCP, with vulnerable, fixed and near-miss variants. Trace and annotate assets, data and action paths, controls, root causes, severity and residual risk; define authorization contexts and write deterministic tests validating vulnerable, fixed and negative behavior; recommend security controls and take part in calibration and peer review.
Engagement: remote contractor assignment lasting up to 2 weeks. At least 4 hours per day and a minimum of 20 hours per week, including 4 hours of overlap with Pacific Time. Pay is up to $150 per hour depending on internal evaluation and location; no minimum is stated. Start date and eligible countries are not stated.
Selection: an AI interview of about 25 minutes, followed by resume/application review and an offer decision.
Requirements
5+ years in application or product security, or security-focused software engineering, including secure code review. Experience with source-to-sink analysis, taint analysis, SAST, CodeQL or Semgrep. Hands-on experience building LLM agents or RAG systems using frameworks such as LangChain, LlamaIndex, OpenAI/Anthropic SDKs or MCP. Strong authorization knowledge: actors, trust boundaries, tenants, OAuth, IAM, identity, permitted data/actions, purposes, recipients, document-level access control. Production coding experience in Python and/or TypeScript, with strong judgment distinguishing genuine SID/EA findings from non-findings. OWASP LLM security risks, MCP, threat modeling or security evaluation experience is a plus.
Eligibility notes
No country or residence restriction stated in the inspected source. Remote does not guarantee worldwide eligibility. Schedule requires at least 4 hours per day, minimum 20 hours per week, with 4 hours of overlap with Pacific Time. Engagement lasts up to 2 weeks. Start date not stated.
Skills
- cyber security
- llm
- code reviews
- code analysis