AI Security Testing Analyst

Alignerr Corp.; São Paulo; A distancia; BRL 276.000 - 828.000; A tiempo parcial

Descripción de la vacante

Alignerr Corp. is seeking security-minded professionals to stress-test, probe, and harden AI systems under an hourly contract. Remote work with 10–40 hours per week, you will think like an attacker, craft adversarial prompts, and document vulnerabilities in structured reports.

You will collaborate asynchronously with engineering teams, stay current on AI security threats, and help refine testing rubrics and protocols to improve safety for millions of users.

Formación

• Solid understanding of cybersecurity concepts and threat modeling.
• Experience with pen-testing or red-teaming AI systems is a plus.
• Familiarity with AI/ML systems and prompt engineering is desirable.

Responsabilidades

• Conduct red-teaming exercises to uncover security weaknesses in AI systems.
• Craft adversarial prompts and edge-case scenarios to test model guardrails.
• Evaluate AI outputs for safety issues, bias, and policy compliance.
• Document vulnerabilities, unexpected behaviors, and exploits in structured reports.
• Collaborate asynchronously with engineering teams to recommend mitigations.
• Stay current on emerging AI security threats and best practices.
• Help define and refine security evaluation rubrics and testing protocols.

Conocimientos

Cybersecurity concepts

Threat modeling

Penetration testing

AI/ML systems

Prompt engineering

Analytical thinking

Technical writing

Herramientas

Open-source AI platforms

Ethical hacking tools

Descripción del empleo

About The Role

AI systems are only as safe as the people who challenge them. We're looking for security-minded professionals to stress-test, probe, and harden AI systems before they reach millions of users. If you love finding flaws, thinking like an attacker, and making technology safer — this role was built for you.

• Organization: Alignerr
• Type: Hourly Contract
• Location: Remote
• Commitment: 10–40 hours/week

What You'll Do

• Conduct red-teaming exercises to uncover security weaknesses in AI systems
• Craft adversarial prompts and edge-case scenarios to test model guardrails
• Evaluate AI outputs for safety issues, bias, and policy compliance
• Document vulnerabilities, unexpected behaviors, and exploits in structured reports
• Collaborate asynchronously with engineering teams to recommend mitigations
• Stay current on emerging AI security threats, jailbreak techniques, and best practices
• Help define and refine security evaluation rubrics and testing protocols

Who You Are

• You have a solid understanding of cybersecurity concepts, threat modeling, or penetration testing
• You've worked with AI/ML systems, LLMs, or prompt engineering — or you're eager to learn
• You're a creative, analytical thinker who enjoys breaking things to make them better
• You communicate clearly and document findings in structured, professional formats
• You're comfortable working independently on asynchronous, task-based assignments
• Familiarity with open-source AI platforms or ethical hacking tools is a plus
• A background in infosec, ethical hacking, or AI safety research is a bonus — not a requirement

Why Join Us

• Shape AI safety at scale — your work directly improves AI products used by millions of people
• Work at the frontier — collaborate with top research labs on cutting-edge AI security challenges
• Full flexibility — set your own hours and work from anywhere in the world
• Grow fast — build deep expertise in one of the fastest-growing and highest-demand domains in tech
• Ongoing opportunity — strong performers are considered for expanded scope and contract extensions
• Meaningful work — every vulnerability you find makes AI a little safer for everyone