NLP Performance Engineer
At a glance
Mid-level Machine Learning Engineering role at G-Research. London · full-time · no salary stated · we estimate £60,000–£97,524 across the United Kingdom.
G-Research has not published a salary for this role. The figure below is our estimate, not theirs.
aimlroles summary, based on the employer's posting.
What you'll do
- Measure and tune large-scale LLM inference across the firm’s compute infrastructure
- Adapt model deployment and inference software to run efficiently on different GPU architectures
- Implement inference improvements while preserving the quality of model outputs
- Build reusable implementations, libraries and tools that make NLP workloads more efficient and dependable
- Work with researchers and platform teams on optimized designs and longer-term compute decisions
What you bring
- A computer science degree at bachelor’s level or above, or equivalent practical experience
- A track record of measuring and improving performance for large-scale LLM inference
- Strong knowledge of transformer serving, including prefill and decode, KV caches, attention methods and bottlenecks
- Practical experience with an LLM serving framework and PyTorch, plus inference methods such as quantisation or speculative decoding
- Software engineering ability in Python and CUDA, including building reliable machine-learning systems
Who this fits
This hands-on quantitative development role suits an engineer focused on LLM inference performance who works well with research and infrastructure teams. The role is based in London.
From the employer
We tackle the most complex problems in quantitative finance, by bringing scientific clarity to financial complexity.
From our London HQ, we unite world-class researchers and engineers in an environment that values deep exploration and methodical execution, because the best ideas take time to evolve. Together we're building a world-class platform to amplify our teams' most powerful ideas.
As part of our engineering team, you'll shape the platforms and tools that drive high-impact research, designing systems that scale, accelerate discovery and support innovation across the firm.
Take the next step in your career.
The role
G-Research is investing in how we apply large language models (LLMs) and other Natural Language Processing (NLP) techniques across the firm. We are looking for an exceptional NLP Performance Engineer to join our NLP Engineering team and take ownership of large-scale LLM inference performance.
This is a specialist Quantitative Developer role. Like all our Quantitative Developers, you will work alongside researchers to bring their ideas to life, with a particular focus on maximising the performance of LLMs.
This is a hands-on, high-impact role. You will design and implement techniques that improve the performance, cost-efficiency and capabilities of inference workloads on cutting-edge compute infrastructure, enabling researchers and engineers to make the best use of current and future systems.
Working closely with research teams and infrastructure engineers, you will profile and analyse workloads, eliminate bottlenecks and develop reference solutions. Your work will help shape the tooling and infrastructure that underpins our NLP capabilities.
Key responsibilities of the role include:
- 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
Who are we looking for?
We're looking for an engineer who combines deep knowledge of LLM inference with strong software engineering skills and a scientific approach to performance.
The ideal candidate will have the following skills and experience:
- 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
Why join us?
- Highly competitive compensation plus annual discretionary bonus
- Lunch provided (via Just Eat for Business) and dedicated barista bar
- 35 days’ annual leave
- 9% company pension contributions
- Informal dress code and excellent work/life balance
- Comprehensive healthcare and life assurance
- Cycle-to-work scheme
- Monthly company events
G-Research is committed to cultivating and preserving an inclusive work environment. We are an ideas-driven business and we place great value on diversity of experience and opinions.
We want to ensure that applicants receive a recruitment experience that enables them to perform at their best. If you have a disability or special need that requires accommodation please let us know in the relevant section