Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
TuringPosted 12 days ago

GenAI Security Evaluation Engineer

Remote (Global)RemoteContract
Who we'd reach at TuringFound and reached by Power Apply
Best leadEngineering manager

Leads the team you would join

Technical recruiter

Owns the opening

Team member

On the team, can refer you

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a remote contractor role, open worldwide, for an experienced application security engineer who will build and assess security test tasks for generative AI applications. The work involves creating vulnerable and patched versions of agent and retrieval-augmented generation systems, tracing data and action flows, and writing tests that show whether a fix holds. The engagement lasts up to two weeks and requires at least 20 hours a week, with 4 hours of overlap with Pacific Time. Turing supplies data and expert services to frontier AI labs and enterprises.

What you’ll do

  • Source or build GenAI applications, including agent and RAG systems.
  • Create vulnerable versions of those applications and patched counterparts.
  • Document findings with exact code spans, traps, control status, and fixes.
  • Trace data and action flows across files, callbacks, registries, and background jobs to find where a control misses a route.
  • Define authorization contexts covering actors, trust boundaries, tenants, permitted data and actions, purposes, recipients, and document access.
  • Write exploit and reproduction tests that separate vulnerable behavior from patched behavior.
  • Run the relevant model path against a live model where practical.

What they’re looking for

  • 3+ years in application or product security, secure code review, penetration testing, or vulnerability research.
  • Strong data-flow reasoning from source to sink across files, callbacks, and background jobs.
  • Solid authorization knowledge, including least privilege, tenant isolation, and approval flows.
  • Knowledge of the OWASP Top 10 for LLM Applications, especially sensitive information disclosure and excessive agency.
  • Familiarity with prompt injection and tool abuse.
  • Ability to map findings to CWEs such as 200, 201, 532, 284, 285, 862, 863, 250, and 269.
  • Experience writing exploit and reproduction tests.
  • Use of CodeQL or Semgrep and reading SARIF output.
  • Hands-on work with LLM tool calling, agents, MCP, RAG, memory, or tracing, using frameworks such as LangChain or LlamaIndex.
  • Production coding experience, Docker, Git, and reading upstream security patches and commit history.
  • Clear technical English.

Nice to have

  • SWE, OSCP, GWAPT, CSSLP, or similar credentials.
  • CVE credits, bug bounty experience, or published security research.
  • AI red teaming or LLM evaluation experience.

What’s on offer

  • Contractor engagement of up to two weeks.
  • Fully remote work, with at least 20 hours a week and 4 hours of overlap with Pacific Time.

Skills

Application SecurityGenerative AI SecuritySecure Code ReviewPenetration TestingData-Flow AnalysisAuthorizationOWASP Top 10 for LLM ApplicationsPrompt InjectionCWECodeQLSemgrepSARIFLangChainLlamaIndexMCPRAGLLM Tool CallingOpenTelemetry

Questions about this role

Is this role remote?

Yes, it is listed as remote and global.

How long is the engagement?

Up to two weeks, as a contractor.

How much experience is needed?

At least 3 years in application or product security, secure code review, penetration testing, or vulnerability research.