Ai Engineer

Who you are

You have a deep understanding of Generative AI and its main models — you think like an adversary, crafting prompts and scenarios to test model guardrails and exploring creative ways to bypass restrictions. Your expertise allows you to systematically document outcomes and collaborate effectively with engineers and safety researchers to improve system defenses.

You thrive in a collaborative environment, working closely with cross-functional teams to share findings and enhance the security of AI systems. Your analytical mindset enables you to uncover weaknesses in AI models, contributing to the overall safety and reliability of the technology.

What you'll do

As an AI Red Team Engineer at LILT, you will engage in projects focused on adversarial testing of AI systems, including LLMs and multimodal models. Your role will involve crafting innovative testing scenarios and systematically documenting the outcomes to inform improvements in AI defenses. You will collaborate with engineers and safety researchers, sharing insights that will help strengthen the robustness of AI systems.

You will be responsible for thinking creatively to identify potential vulnerabilities in AI models and developing strategies to mitigate these risks. Your work will play a crucial role in ensuring that LILT's AI solutions remain secure and effective in real-world applications.

What we offer

At LILT, we empower our teammates with leading tools and global collaboration opportunities. We are committed to fostering a culture of growth and innovation, where your contributions directly impact the future of AI in communication. Join us in our mission to make the world's information accessible to everyone, regardless of the language they speak.