AI Security Engineer | $30/hr Remote

Crossing Hurdles; Brasil; Teletrabalho; BRL 227 000 - 265 000; Tempo parcial

Resumo da oferta

Crossing Hurdles is seeking a Senior AI Security Engineer focused on LLM vulnerability detection in a remote contract role. You will build runnable agents and RAG repositories to uncover security flaws and test multiple code paths for weaknesses.

You will trace data flows, annotate root causes, define authorization contexts, and help validate security controls. The position requires 20–40 hours weekly and strong expertise in application security and GenAI risk models.

Qualificações

• 5+ years in application security or security-focused software engineering.
• Experience with source-to-sink analysis and taint analysis methods.
• Hands-on experience building LLM agents or RAG systems.
• Strong knowledge of authorization principles and access controls.
• Production coding experience in Python and/or TypeScript.
• Familiarity with OWASP LLM security risks and threat modeling.
• Ability to distinguish genuine security findings from non-findings.

Responsabilidades

• Build runnable agent and RAG repositories for vulnerability detection
• Create various code versions to test for security vulnerabilities
• Trace and annotate assets, data paths, and root causes of vulnerabilities
• Define authorization contexts and write deterministic validation tests
• Recommend security controls and participate in peer review processes
• Evaluate the effectiveness of static analysis tools in GenAI applications
• Explain vulnerabilities through testing and documentation

Conhecimentos

Security testing

Threat modeling

LLM security

Taint analysis

Access controls

Code review

RAG systems

Ferramentas

Python

TypeScript

Descrição da oferta de emprego

Position: Senior AI Security Engineer LLM Vulnerability

Type: Contract

Compensation: $30/h

Location: Remote

Commitment:20 - 40 hours/week

Role Responsibilities

• Build runnable agent and RAG repositories for vulnerability detection
• Create various code versions to test for security vulnerabilities
• Trace and annotate assets, data paths, and root causes of vulnerabilities
• Define authorization contexts and write deterministic validation tests
• Recommend security controls and participate in peer review processes
• Evaluate the effectiveness of static analysis tools in GenAI applications
• Explain vulnerabilities through testing and documentation

Requirements

• 5+ years in application security or security-focused software engineering
• Experience with source-to-sink analysis and taint analysis methods
• Hands-on experience building LLM agents or RAG systems
• Strong knowledge of authorization principles and access controls
• Production coding experience in Python and/or TypeScript
• Familiarity with OWASP LLM security risks and threat modeling
• Ability to distinguish genuine security findings from non-findings