Requirements

A Bachelor’s, Master’s or PhD in computer science, or equivalent experience
Proven experience profiling, benchmarking and optimising large-scale LLM inference workloads
A scientific, evidence-led approach to performance optimisation, using rigorous benchmarking and reproducible measurement
Deep understanding of transformer inference, including prefill versus decode, KV-cache behaviour, attention variants and performance bottlenecks
Hands-on experience with LLM serving frameworks such as vLLM, SGLang, TensorRT-LLM or TGI, and the PyTorch ecosystem
Experience with inference optimisation techniques, including quantisation, speculative decoding and model parallelism across modern GPU architectures
Strong software engineering skills, including Python, CUDA and building reliable systems for machine learning workloads
Strong communication skills, with the ability to collaborate across research, infrastructure and engineering teams

What You'll Be Doing

Profiling, benchmarking and optimising large-scale LLM inference workloads across our compute infrastructure
Ensuring efficient deployment of the latest models across a range of GPU architectures, adapting the inference stack as hardware evolves
Designing and implementing inference optimisations while maintaining output quality
Developing reference implementations, libraries and tooling to improve the efficiency and reliability of NLP workloads
Collaborating with researchers, senior stakeholders and engineers to design optimised solutions
Working with systems, architecture and platform teams to evolve the compute stack and influence long-term platform decisions