AI Security Engineer / Offensive Security Engineer - Technology

TrueLogic
Mexico City
Workplace: RemoteFull timeFunction: CybersecuritySkills: ["Pragmatic judgment","Engineering judgment","Automation mindset","Problem-solving","English communication"]

Continuously red-team an AI product and its supporting infrastructure, APIs, identity, memory, and data flows. Identify, reproduce, and help remediate vulnerabilities while partnering with engineering on hardening and defensive improvements. Use automation, AI agents, and security tooling to probe systems, triage findings by exploitability and business risk, and build an iterative security layer—especially for AI/LLM and agentic attack surfaces like prompt injection and tool misuse.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
TrueLogic
TrueLogic
1 day ago

AI Security Engineer / Offensive Security Engineer - Technology

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 1 hour agoStatus: Live

Job Summary

Continuously red-team an AI product and its supporting infrastructure, APIs, identity, memory, and data flows. Identify, reproduce, and help remediate vulnerabilities while partnering with engineering on hardening and defensive improvements. Use automation, AI agents, and security tooling to probe systems, triage findings by exploitability and business risk, and build an iterative security layer—especially for AI/LLM and agentic attack surfaces like prompt injection and tool misuse.
Location: Mexico City
Workplace: Remote
Employment Type: Full time
Job Function: Cybersecurity

Key Responsibilities

  • •Continuously red-team the company’s product, infrastructure, APIs, and agentic systems.
  • •Identify, reproduce, and remediate vulnerabilities in partnership with engineering.
  • •Test AI-specific attack surfaces including prompt injection, tool misuse, data leakage, permission escalation, memory poisoning, and unsafe agent behavior.
  • •Use agents, automation, and security tooling to continuously probe systems and surface weaknesses.
  • •Triage findings by exploitability, user impact, and business risk; strengthen authentication, authorization, identity, secrets management, data boundaries, and infrastructure security.

Pay and Benefits

Perks:Remote WorkPaid Leave

Key Requirements

  • •Strong experience in application, product, cloud, or offensive security.
  • •Hands-on ability to identify, exploit, debug, and remediate vulnerabilities.
  • •Solid understanding of modern web architecture, APIs, authentication/authorization, cloud infrastructure, and data security.
  • •Enough coding ability to build security tooling and automation for security testing and remediation.
  • •Familiarity with AI/LLM security risks and interest in securing agentic systems; experience red-teaming LLM/agent systems is valuable.
Experience:Offensive securityApplication securityCloud securityAI/LLM securityAgentic systems
Skills:Pragmatic judgmentEngineering judgmentAutomation mindsetProblem-solvingEnglish communication
Languages:English

Company Brief

TrueLogic
TrueLogic builds custom web and mobile applications, offering product engineering, UX/UI design, and team augmentation services. They partner with startups and enterprises to deliver scalable software solutions, cloud integrations, and ongoing technical support.
Industry: Professional Services
Website