Cybersecurity Experts for AI Training

Gramian Consulting; Brasil; Hybrid; BRL 392,927 - 589,390; Part time

Job summary

Gramian Consulting is seeking experienced Cybersecurity Experts to build security-focused coding scenarios for evaluating AI systems. This hands-on role focuses on security benchmark development and complex attack surface evaluations across languages like Go, Python, and Node.js.

Ideal candidates should have 4+ years in cybersecurity and a strong grasp of web security vulnerabilities. The position is geared towards teamwork in developing reproducible environments and conducting adversarial testing.

Qualifications

• 4+ years of experience in cybersecurity, application security, vulnerability research, or offensive security.
• Strong understanding of web security, authentication, OAuth, injection attacks, and access control vulnerabilities.
• Experience with cryptographic vulnerabilities, filesystem attacks, or privilege escalation scenarios.

Responsibilities

• Design vulnerable multi-component applications and security challenge environments.
• Develop realistic exploit chains combining multiple vulnerability categories.
• Collaborate with teams on AI evaluation, benchmarking, and testing systems.

Skills

Vulnerability discovery

Exploit development

Secure code review

Web security

Docker

Coding in Go, Python, Node.js, Rust

Tools

SAST

Fuzzers

IAST

Job description

Role Overview

We are looking for experienced Cybersecurity Experts to contribute to the development of advanced evaluation environments for frontier AI systems. In this role, you will create realistic security-focused coding scenarios that assess how AI models understand software vulnerabilities, exploit chains, secure coding practices, and complex attack surfaces. The work combines offensive security, application security, software engineering, and AI evaluation. This is a highly technical, hands‑on opportunity focused on building reproducible security benchmarks and adversarial testing environments inspired by real‑world vulnerability patterns.

Commitments

8 hours per day with an overlap of 4 hours with PST.

Employment Type

Contractor assignment (no medical/paid leave).

Duration

4 weeks+.

Location

Bangladesh, Brazil, Colombia, Egypt, Ghana, India, Pakistan, Indonesia, Kenya, Nigeria, Turkey, Vietnam.

Interview

2x technical interviews.

Responsibilities

• Design vulnerable multi-component applications and security challenge environments across languages such as Go, Python, Node.js, or Rust
• Develop realistic exploit chains combining multiple vulnerability categories and attack vectors
• Build deterministic evaluation environments using Docker and automated validation tooling
• Create security-focused test cases and verification logic for vulnerability detection and remediation workflows
• Review and analyze AI-generated outputs to identify gaps in reasoning, security understanding, or exploit detection
• Develop adversarial scenarios involving misleading documentation, obfuscated code, edge cases, and hidden attack paths
• Model real-world vulnerability classes inspired by CVEs, bug bounty findings, and production security incidents
• Ensure evaluation tasks remain scalable, reproducible, and resistant to contamination from public datasets
• Collaborate with cross-functional teams working on AI evaluation, benchmarking, and automated testing systems

Requirements

• 4+ years of experience in cybersecurity, application security, vulnerability research, or offensive security
• Hands‑on experience with vulnerability discovery, exploit development, secure code review, or patch validation
• Strong understanding of web security, authentication, sessions, OAuth, JWT, SSRF, injection attacks, and access control vulnerabilities
• Experience with cryptographic vulnerabilities, filesystem attacks, or privilege escalation scenarios
• Experience using security tools such as SAST, fuzzers, IAST, or similar security testing frameworks
• Strong coding skills in at least two of the following languages: Go, Python, Node.js, Rust
• Experience working with Docker and containerized environments
• Familiarity with Linux internals and system-level behavior
• Experience with bug bounty programs, CTFs, red teaming, or CVE research is a strong plus