AI Red Team Engineer — LLM Security & Pentesting (C1 English)

We’re hiring multiple AI Red Team Engineers with a strong cybersecurity/pentesting background and hands-on LLM security expertise. Ideal candidates are proficient in Python/Bash/PowerShell, containerization and CI/CD security (e.g., Docker), and have experience across web/API/network/infrastructure testing. You understand LLM attack surfaces (prompt injection, jailbreaks, data exfiltration) and the OWASP Top 10 for LLMs, can use/red-team with frameworks like garak or PyRIT, and can communicate clearly in advanced (C1) English. Availability to complete a HackerRank + platform assessment ASAP is required.

In this project you will design and execute adversarial evaluations of LLMs, agents, and RAG pipelines: crafting & automating attack prompts, building test suites, probing function-calling/tool use, defining scoring rubrics, grading model behaviors, documenting reproducible findings with risk ratings, proposing mitigations, and contributing small scripts/utilities to scale testing. You’ll collaborate in a remote, part-time contract capacity, follow detailed guidelines, and uphold strict ethical and safety standards.