AI Inference Internship

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 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)

Schedule

• Internship program: 13 weeks, full-time or part-time, in-person in London office (hybrid schedule: 3 days from the office, 2 days WFH)

Interview Process

• Fill out the application on Perplexity website
• If selected, People Ops and technical interviews will be involved.
• Offer. We’re impressed! We’d love to welcome you to our Internship program!
• Start. We have a desk waiting for you in our London office!

FAQ

Do you sponsor visas? Can I apply if I need a visa to work in the UK?

→ Unfortunately we are unable to sponsor visas

What if I’m on a student visa?

→ You need to seek approval from your University (to determine if you are eligible to work full time or part time only)

How many internship spots are there?

• We have spots for 2-3 interns in our 2026 class.

Is housing provided?

• Unfortunately we cannot provide housing.

Is health insurance provided?

• Unfortunately we cannot provide health insurance for interns. Full time employees receive full health insurance and benefits.

How many full time offers are available at the end of the residency?

• There is no limit. All outstanding performers will be given a full time offer!

At Perplexity, we've experienced tremendous growth and adoption since publicly launching the world's first fully functional conversational answer engine in 2022. We've grown from answering 2.5 million questions per day at the start of 2024 to around 20 million daily queries in December 2024. We also offer Perplexity Enterprise Pro, which counts leading companies like Nvidia, the Cleveland Cavaliers, Bridgewater, and Zoom as customers.

To support our rapid expansion, we've raised significant funding from some of the most respected technology investors. Our investor base includes IVP, NEA, Jeff Bezos, NVIDIA, Databricks, Bessemer Venture Partners, Elad Gil, Nat Friedman, Daniel Gross, Naval Ravikant, Tobi Lutke, and many other visionary individuals. In 2024, our employee base grew nearly 300%, and we're just getting started.

Final offer amounts are determined by multiple factors, including experience and expertise, and may vary from the amounts listed above.