Remote AI Security Engineer, LLM Vulnerabilities (contract)

Pay: $20 per hour, 20 or 40 hours a week for about 4 weeks, with 4 hours overlapping US Pacific time. You'll build small LLM agent and RAG codebases with realistic security flaws (sensitive information disclosure, excessive agency) plus fixed versions, then trace, annotate and write tests for each finding. You need: security experience (application security, secure code review, penetration testing or security engineering) and Python or TypeScript. Hands-on work with LLM agents, RAG or MCP is a strong plus. A LinkedIn profile. Open to people based in Bangladesh, Brazil, Colombia, Egypt, Ghana, India, Indonesia, Nigeria, Turkey and the United States. If you have applied to this work through another agency or directly with the hiring partner in the last 3 months, please don't apply again. Originally posted on Himalayas