AI Inference Internship

Perplexity is excited to announce the Internship Program for exceptional Master’s or PhD students studying Computer Science or Engineering in the UK, enrolled in the 2025-2026 academic year. This is an intensive program in which you will work directly with our AI Inference team. This program offers a unique opportunity to gain valuable experience in a rapidly growing AI startup. Outstanding performers might be offered a full time position at the end of the program. Our AI Inference team is responsible for running the models behind the Perplexity products. The team maintains the inference engine and deployments behind models ranging from single-node embeddings to distributed sparse Mixture-of-Experts models, maintaining large GPU clusters. With a keen focus on latency and throughput, the Inference team is responsible for the entire serving stack, from GPU kernels to networking and monitoring infrastructure. Responsibilities - Work with the inference team to improve serving latency and throughput - Bring up support for new models and state-of-the art inference optimizations or quantization schemes - Optimize inference across the entire stack, from GPU kernels to serving endpoints Qualifications - Strong engineering track record with proven knowledge of fundamentals and programming languages (multi-threaded programming, networking, compilation, systems programming, etc) - Pursuing