Remote GenAI Security Engineer — SAST & LLM Agents
Posted Updated
Description
Gramian Consultancy is seeking a Senior Application Security Engineer to lead GenAI security evaluation efforts. You will assess static analysis tools against LLM agents and RAG applications, building runnable samples showing SID and EA vulnerabilities, with deterministic tests and documented findings.
You will analyze data flows, authentication contexts, and authorization models, ensuring robust security controls and clear remediation guidance across multi-tenant environments.
Build runnable agent and RAG repositories containing code-reachable vulnerabilities (SID/EA). Develop realistic security scenarios involving tool calling, agent memory, MCP, and LLM components. Create vulnerable, fixed, and negative code variants with minimal security differences. Evaluate SAST tools and assess their accuracy in detecting real vulnerabilities. Perform source-to-sink analysis and trace data flows, action paths, and trust boundaries. Annotate findings with assets, root causes, controls, severity, and residual risk. Define authorization contexts covering actors, tenants, identities, data, actions, purposes, recipients. Develop deterministic tests to validate vulnerable, fixed, and negative security behaviors. Recommend security controls and remediation approaches. Participate in calibration, peer reviews, and QA activities. 5+ years of professional experience in application security, product security, or security-focused software engineering. Strong experience conducting secure code reviews and identifying application-level vulnerabilities. Hands-on experience building LLM agents or RAG applications. Production-level coding experience in Python and/or TypeScript. Familiarity with LangChain, LlamaIndex, OpenAI or Anthropic SDKs, and Model Context Protocol (MCP).Skills
Sign in to read and join the discussion.