Ai Engineer

Who you are

You have a deep understanding of generative AI and its main models — you think like an adversary and are skilled at crafting prompts and scenarios to test model guardrails. Your expertise allows you to explore creative ways to bypass restrictions and systematically document outcomes. You thrive in collaborative environments, working closely with engineers and safety researchers to share findings and enhance system defenses.

You possess strong analytical skills and a keen eye for detail — your ability to identify weaknesses in AI systems is complemented by your experience in adversarial testing. You are comfortable navigating complex AI technologies and have a passion for improving the safety and reliability of AI applications.

What you'll do

In this role, you will collaborate on projects focused on adversarial testing of AI systems, including LLMs, multimodal models, and inference services. Your primary responsibility will be to craft prompts and scenarios that challenge the AI's guardrails, helping to uncover vulnerabilities that could be exploited. You will document your findings meticulously, providing valuable insights to improve the robustness of AI systems.

You will work alongside engineers and safety researchers, sharing your discoveries and contributing to the development of stronger defenses against potential adversarial attacks. Your work will play a crucial role in ensuring that LILT's AI technologies remain secure and effective in real-world applications.

What we offer

LILT is committed to fostering a collaborative and innovative work environment. As part of our team, you will have access to cutting-edge tools and resources that empower you to do your best work. We value growth opportunities and encourage our teammates to continuously develop their skills and expertise. Join us in our mission to make the world's information accessible to everyone, regardless of the language they speak.