UK Internship Program
UK Internship Program
Perplexity
Perplexity is offering an Internship Program for exceptional Master's or PhD students in Computer Science or Engineering in the UK. Interns will work with the AI Inference team, focusing on improving model serving latency and throughput in a rapidly growing AI startup. Successful interns may receive full-time job offers at the end of the program.
Qualification
- Strong engineering track record with knowledge of programming fundamentals
- Pursuing a Master's or PhD in Computer Science focusing on performance-related subjects
- Experience with ML frameworks such as Torch or JAX
- Experience with GPU programming using CUDA or Triton
- Experience with High-Performance Computing (OpenMPI)
Responsibility
- Work with the inference team to improve serving latency and throughput
- Support new models and state-of-the-art inference optimizations or quantization schemes
- Optimize inference across the entire stack, from GPU kernels to serving endpoints
- Maintain large GPU clusters for model inference
- Collaborate with team members on performance-related projects
