About the job
Perplexity is thrilled to introduce our Internship Program, designed for outstanding Master’s or PhD students specializing in Computer Science or Engineering in the UK for the 2025-2026 academic year. This immersive program offers a direct collaboration with our AI Inference team, providing a distinctive opportunity to acquire invaluable experience within a rapidly expanding AI startup. Exceptional interns may receive an offer for a full-time position upon completion of the program.
Our AI Inference team is integral to the performance of Perplexity's products, overseeing the inference engine and deployments for models ranging from single-node embeddings to advanced distributed sparse Mixture-of-Experts models, all while managing extensive GPU clusters. With a focus on optimizing latency and throughput, the Inference team encompasses the entire serving stack, from GPU kernels to networking and monitoring infrastructure.

