Ai Engineer

Who you are

You have a deep understanding of generative AI and the main models used in the industry — your expertise allows you to think critically about AI systems and their vulnerabilities. You are skilled in crafting prompts and scenarios that effectively test model guardrails, exploring creative ways to bypass restrictions. Your experience in adversarial testing equips you to systematically document outcomes and share findings with engineering and safety researchers.

You thrive in collaborative environments, working closely with engineers and researchers to improve system defenses — your ability to communicate complex ideas clearly helps bridge the gap between technical and non-technical stakeholders. You are detail-oriented and methodical in your approach, ensuring that all aspects of the testing process are thoroughly documented and analyzed.

What you'll do

In this role, you will collaborate on projects focused on adversarial testing of AI systems, including LLMs and multimodal models. You will craft prompts and scenarios to test model guardrails, systematically documenting outcomes to uncover weaknesses. Your work will involve thinking like an adversary to explore creative ways to bypass restrictions, contributing to the overall improvement of system defenses.

You will engage with engineers and safety researchers to share your findings, fostering a culture of continuous improvement and innovation within the team. Your insights will play a crucial role in enhancing the robustness of AI systems, ensuring they are resilient against potential threats.

What we offer

At LILT, you will be part of a mission-driven company that is redefining the translation market through AI. We empower our teammates with leading tools and global collaboration opportunities, fostering an environment where you can do your best work. Join us in making the world's information accessible to everyone, regardless of the language they speak.