Senior AI Security Engineer | $100/task
Senior AI Security Engineer – LLM Vulnerability
Experience: 3+ Years
Job Type: Contractor
Location: Remote
Compensation: $100 per task
Role Overview:
We are looking for experienced GenAI Security Engineers to build and evaluate security tasks for LLM, agent, and RAG-based applications. The role involves creating vulnerable and patched versions of GenAI applications, tracing security issues, writing exploit/reproduction tests, and evaluating whether security controls work correctly.
Key Responsibilities:
Build or review GenAI, Agent, and RAG applications.
Create vulnerable versions and secure patched counterparts.
Trace data and action flows across application components.
Define authorization contexts, trust boundaries, permissions, and access controls.
Write exploit and reproduction tests for security vulnerabilities.
Document findings, affected code paths, controls, and remediation recommendations.
Demonstrate vulnerable model behavior using live models where possible.
Key Requirements:
3+ years in Application Security, Product Security, Penetration Testing, Secure Code Review, or Vulnerability Research.
Strong understanding of authentication, authorization, least privilege, tenant isolation, and trust boundaries.
Knowledge of OWASP Top 10 for LLM Applications, especially Sensitive Information Disclosure and Excessive Agency.
Familiarity with prompt injection, tool abuse, CWE mapping, and exploit testing.
Experience with CodeQL, Semgrep, SARIF, Docker, and Git.
Hands-on knowledge of LLM agents, MCP, RAG, memory, tool calling, and tracing.
Experience with tools/frameworks such as LangChain, LlamaIndex, OpenAI/Anthropic SDKs, and Open
Telemetry.
Selection Process: ICFProfile Review Assessment for approved candidates