Skip to content
AI Trainer Jobs
Companies

App Security Expert

micro1 · 100% remote · Contract · Posted

Pay
$40–80/hr
Location
Worldwide
Languages
English
Hours
Flexible
Openings
10
Level
Expert
Apply for this position

Summary

Design and implement security-focused application fixtures and test cases to train AI systems on application security, including creating answer keys and evaluating pipeline methodologies. Document insights and collaborate with peers to improve agent-based security evaluation.

What you'll do

  • Design and implement application fixtures with embedded security vulnerabilities or secure solutions
  • Develop deterministic test cases and security-context manifests
  • Create hidden answer keys for AI or scanner evaluation of vulnerable versus secure code
  • Evaluate and iterate on pipeline methodologies for synthetic tasks and fixtures
  • Document technical insights and methodologies
  • Collaborate through written and verbal communication and review peer contributions
  • Engage with agent-based security architecture and improve the evaluation pipeline

Requirements

  • Apply extensive application security or secure software development expertise
  • Demonstrate understanding of OSWE, LLM security, AI-SAST, and AppSec best practices
  • Design or evaluate security architecture for traditional and agent-based applications
  • Build, secure, and test application codebases and remediate advanced vulnerabilities
  • Write precise technical documentation and provide collaborative feedback
  • Use synthetic security fixtures and deterministic testing approaches

Skills

  • OSWE
  • LLM Security
  • AI-SAST Evaluation
  • AppSec
  • Agent Security Architecture

Full description

Role Title: App Security Expert


Role Type: Contractor


Location: Remote


micro1 is engaging App Security Experts to contribute to a customer’s dynamic project focused on real-world application security. In this role, you'll apply your expertise to help train next-generation AI systems. Your work will shape how models learn, reason, and perform through high-quality, real-world input. No prior experience in AI is required — your domain knowledge is what matters.


Scope of Work

  1. Design and implement small, purpose-built application fixtures with embedded security vulnerabilities or secure solutions, specifically addressing OWASP LLM risks such as Sensitive Information Disclosure and Excessive Agency.
  2. Develop deterministic test cases and security-context manifests to robustly assess application security posture.
  3. Create detailed hidden answer keys to enable accurate AI or scanner evaluation of vulnerable versus secure code.
  4. Evaluate and iterate on pipeline methodologies to ensure synthetic tasks and fixtures are challenging yet realistic for AppSec assessment.
  5. Document technical insights and methodologies, ensuring clarity in written feedback and communication.
  6. Collaborate through clear and thorough written and verbal communication to share findings and review peer contributions.
  7. Engage with agent-based security architecture and contribute to continuous improvement of the evaluation pipeline.


Preferred Qualifications

  1. Extensive experience (ideally 5+ years) in application security, secure software development, or CyberSWE roles.
  2. Strong understanding of OSWE, LLM security, AI-powered static analysis (AI-SAST), and AppSec best practices.
  3. Proven track record designing or evaluating security architecture for traditional and agent-based applications.
  4. Expertise in building, securing, and testing application codebases, including identifying and remediating advanced vulnerabilities.
  5. Exceptional written and verbal communication skills, with a focus on precise technical documentation and collaborative feedback.
  6. Experience with synthetic security fixtures and deterministic testing approaches is highly desirable.
  7. Demonstrated ability to deliver thoughtful insights and actionable security recommendations in a remote contribution context.

Similar jobs

View all jobs