Project Overview:

Join a growing community of professionals advancing the next wave of AI. As an AI Trainer, you’ll play a hands-on role by analyzing and providing feedback on data to improve LLM performance, helping ensure that the next generation of AI technology is accurate and trustworthy.

We are seeking a skilled Security Engineering Expert to work as a project consultant in our AI Labor Marketplace. This is not a full-time employment position — you will be engaged as an expert project consultant on a contract basis.

Location: U.S.-based experts only

Engagement: Part-time, project-based expert evaluation work

Work Type: Remote

Project Summary:

Contributors will create challenging, terminal-based cybersecurity tasks used to evaluate advanced AI systems. Relevant specialties include digital forensics, cryptography, application security, security research, and reverse engineering.

Each contributor will own their task end to end: defining a difficult but fair security problem, building a reproducible Docker environment, implementing a correct reference solution, and developing hidden tests or verifiers that reliably determine whether the task was genuinely solved.

This work is intended for experienced security engineers and researchers who are strong hands-on programmers. Contributors must be capable of independently solving the technical problems they design and thinking adversarially about ways an AI agent could produce an apparently successful result without satisfying the underlying security or correctness requirements.

Consultant Engagement Terms:

This is a project-based consultant role. Consultants will be paid on a per-project basis; hourly rates are estimates based on anticipated completion time. Consultants control their own schedule, provide their own tools, and may simultaneously provide services to other vendors or employers (subject to those vendors’ allowances).

Responsibilities:

Contributors will:

• Design technically challenging but fair security problems grounded in their area of expertise.
• Write precise, self-contained task instructions and objective success criteria.
• Build isolated, reproducible task environments using Docker.
• Implement complete and correct reference solutions.
• Develop robust hidden tests or verifiers that validate genuine technical correctness.
• Anticipate shortcuts, hard-coded outputs, incomplete solutions, false positives, and other approaches that could incorrectly satisfy superficial checks.
• Test relevant edge cases and failure modes.
• Validate that the reference solution passes while the untouched task environment fails.
• Address technical review feedback affecting task correctness, reproducibility, or verifier quality.

Expected Outcomes:

• Complete terminal-based security evaluation tasks.
• Clear and reproducible task specifications.
• Working reference implementations.
• Dockerized environments containing the necessary dependencies and configuration.
• Automated hidden tests or robust correctness verifiers.
• Validation demonstrating that the reference implementation passes and the baseline task does not.

Qualifications:

• 5+ years of relevant hands-on security engineering or security research experience.
• Deep expertise in at least one applicable discipline, such as digital forensics, cryptography, application security, security research, or reverse engineering.
• Strong hands-on programming ability in languages relevant to the candidate’s specialty.
• Ability to independently solve and implement the difficult technical problems they design.
• Demonstrated experience debugging, analyzing, testing, or reverse-engineering software or systems.
• Strong automated testing and validation skills.
• Ability to reason adversarially about potential false positives and ways incomplete or incorrect solutions could circumvent weak evaluation criteria.
• Experience with Git and GitHub workflows.
• Experience building or debugging Docker-based environments.
• Familiarity with CI/CD or automated build/test workflows.
• Ability to convert complex security requirements into objective, machine-verifiable success criteria.

LinkedIn Data Security and Privacy Notice:

https://legal.linkedin.com/content/dam/legal/Global-Data-Privacy-Notice_LI_TalentCommunity.pdf