AI Software Engineer – Evaluation Platform – ON-SITE

Job Overview

Perplexity is changing the way people search the internet and we are seeking a founding engineer for a new team that will change how Perplexity employees search through internal data. Our team behind Deep Research and other cutting edge AI features is looking for a full stack engineer that is passionate about building evaluation platform for LLM answers and Agent behaviors. You will be partnering with AI engineers to redefine the debugging and evaluation of answer quality tooling process to supercharge our AI development. If you value working on greenfield projects and enjoy high levels of ownership, this is the right role for you. Responsibilities include building new 0-1 full-stack platform for debugging and evaluating LLM outputs, designing intuitive front-end interfaces and robust back-end systems for monitoring the performance of AI product and AI systems, collaborating with researchers and engineers to understand their needs and deliver effective full-stack solutions, continuously improving existing tools and developing new features to meet evolving requirements, and working closely with Engineers, Product, Design, and Data to ensure deep insights into Perplexity’s performance. Qualifications include strong experience in full-stack software development, self-motivation with a willingness to take ownership of tasks, good quantitative understanding of data and visualization, strong communication skills and the ability to work collaboratively in a team environment, and 3+ years of industry experience. Bonus: Experience working with generative AI tools or LLMs. The company has experienced tremendous growth and adoption since publicly launching the world’s first fully functional conversational answer engine in 2022, with significant funding from respected technology investors and a rapidly growing employee base.