NLP Performance Engineer: Scale LLM Inference for Research

Barlowe LLP; Greater London; On-site; GBP 90,000 - 150,000; Full time

Benefits offered by this job

Competitive compensation + bonus

Lunch provided

35 days annual leave

9% pension contributions

Casual dress code

Healthcare & life assurance

Cycle-to-work

Monthly company events

Job summary

G-Research is seeking an exceptional NLP Performance Engineer to own large-scale LLM inference performance within our NLP Engineering team at the London HQ. You will profile, optimise and implement techniques to maximise inference throughput and cost-efficiency, collaborating with researchers and infrastructure engineers to shape scalable tooling and compute stacks.

The role blends high-impact hands-on work with systems design, offering a competitive package and a dynamic research-driven

Qualifications

• 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 with rigorous benchmarking.

Responsibilities

• Profiling, benchmarking and optimising large-scale LLM inference workloads across compute infrastructure.
• Ensuring efficient deployment of latest models across GPU architectures.
• Designing and implementing inference optimisations while maintaining output quality.
• Developing reference implementations, libraries and tooling for NLP workloads.
• Collaborating with researchers and engineers to design optimised solutions.
• Working with systems and platform teams to evolve the compute stack.

Skills

LLM inference

Profiling

Benchmarking

Transformer inference

Python

CUDA

PyTorch

Model parallelism

Quantisation

Speculative decoding

SGLang

vLLM

TensorRT-LLM

Communication skills

Software engineering

Education

Bachelor/Master/PhD in CS

Tools

PyTorch ecosystem

LLM serving frameworks

Job description

G-Research is seeking an exceptional NLP Performance Engineer to own large-scale LLM inference performance within our NLP Engineering team at the London HQ. You will profile, optimise and implement techniques to maximise inference throughput and cost-efficiency, collaborating with researchers and infrastructure engineers to shape scalable tooling and compute stacks.

The role blends high-impact hands-on work with systems design, offering a competitive package and a dynamic research-driven