Stelle · Intern

AI Inference Internship

AI / ML Engineer • Praktikant • Remote • Vollzeit • 📍 London

Perplexity offers a 13-week internship for exceptional Master's or PhD students in Computer Science or Engineering in the UK, working directly with the AI Inference team responsible for running the models behind Perplexity's products. The team maintains the inference engine and deployments for models ranging from single-node embeddings to distributed sparse Mixture-of-Experts models on large GPU clusters, owning the entire serving stack with a focus on latency and throughput. The program is in-person in London (hybrid: 3 days office, 2 days WFH), with 2-3 spots in the 2026 class, and strong performers may receive a full-time offer.

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

Requirements

▹Strong engineering track record with proven knowledge of fundamentals and programming languages (multi-threaded programming, networking, compilation, systems programming, etc.)
▹Pursuing a Master's or PhD in Computer Science with a focus on performance-related subjects (HPC, Compilers, Distributed Systems)
▹Experience with ML frameworks (Torch, JAX)
▹Experience with GPU programming (CUDA, Triton)
▹Experience with High-Performance Computing (OpenMPI)

What we offer

▹13-week internship, full-time or part-time, in-person in the London office (hybrid: 3 days office, 2 days WFH)
▹Possibility of a full-time offer for outstanding performers

Education: Pursuing a Master's or PhD in Computer Science or Engineering (enrolled in the 2025-2026 academic year in the UK), with a focus on performance-related subjects (HPC, Compilers, Distributed Systems)