App Security Expert, Remote - Contract

Requirements

• OSWE (Offensive Web Security Expert) certification or equivalent expertiseMust
• LLM security expertiseMust
• AI-SAST (AI-powered Static Application Security Testing) evaluation knowledgeMust
• Application security (AppSec) fundamentals and practicesMust
• Agent security architecture design and implementationMust
• Written and verbal communication skills for technical documentationMust
• 5+ years application security, secure software development, or CyberSecurity software engineering experience
• Experience designing or evaluating security architecture for agent-based applications
• Experience building, securing, and testing application codebases
• Experience with synthetic security fixtures and deterministic testing approaches

What you'll do

• Design and implement application security fixtures with embedded vulnerabilities
• Develop deterministic test cases and security-context manifests for application assessment
• Create answer keys and evaluation criteria for secure versus vulnerable code assessment
• Evaluate and iterate on security evaluation pipeline methodologies
• Identify and remediate advanced vulnerabilities in application codebases
• Address OWASP LLM risks including Sensitive Information Disclosure and Excessive Agency
• Engage with agent-based security architecture evaluation and improvement
• Clear communication and collaboration in remote work environments
• Document technical insights, methodologies, and security findings
• Provide precise technical feedback and actionable security recommendations
• Review and collaborate on peer contributions and security assessments

Keywords

About the role

Role Title: App Security Expert Role Type: Contract Location: Remote 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. Required Skills: OSWE, LLM security, Ai-sast evaluation, Appsec, Agent security architecture Scope of Work • 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. • Develop deterministic test cases and security-context manifests to robustly assess application security posture. • Create detailed hidden answer keys to enable accurate AI or scanner evaluation of vulnerable versus secure code. • Evaluate and iterate on pipeline methodologies to ensure synthetic tasks and fixtures are challenging yet realistic for AppSec assessment. • Document technical insights and methodologies, ensuring clarity in written feedback and communication. • Collaborate through clear and thorough written and verbal communication to share findings and review peer contributions. • Engage with agent-based security architecture and contribute to continuous improvement of the evaluation pipeline. Preferred Qualifications • Extensive experience (ideally 5+ years) in application security, secure software development, or CyberSWE roles. • Strong understanding of OSWE, LLM security, AI-powered static analysis (AI-SAST), and AppSec best practices. • Proven track record designing or evaluating security architecture for traditional and agent-based applications. • Expertise in building, securing, and testing application codebases, including identifying and remediating advanced vulnerabilities. • Exceptional written and verbal communication skills, with a focus on precise technical documentation and collaborative feedback. • Experience with synthetic security fixtures and deterministic testing approaches is highly desirable. • Demonstrated ability to deliver thoughtful insights and actionable security recommendations in a remote contribution context. Originally posted on Himalayas