Salary: £40,000 - 70,000 per year Requirements:
* ###
* We are seeking candidates who possess a deep understanding of large-scale machine learning systems engineering, with direct experience in deploying or optimizing large language models (LLMs). You should have hands-on expertise in programming languages such as C++, Rust, or Go for systems programming, as well as proficiency in Python for model integration. A strong knowledge of distributed runtimes and scheduling frameworks, such as Ray, Dask, or MPI, is essential. Additionally, experience with GPU cluster management, including CUDA and performance tuning across accelerators, is necessary. A solid grasp of cloud-native orchestration, including Docker and Kubernetes, along with observability tooling like Prometheus and Grafana, is also required. We value proven ability to translate cutting-edge research into scalable engineered solutions.
* ###
Responsibilities:
* In this role, you will design cloud-native architectures to run large language models on serverless frameworks, such as Kubernetes or Knative. You will develop approaches to minimize cold-start latency through techniques like advanced container snapshotting and weight pre-loading. Your responsibilities will include building distributed inference pipelines with tensor parallelism and model sharding to efficiently serve LLMs at scale. You will experiment with quantization and pruning to maximize throughput from GPU and accelerator clusters, all while collaborating closely with applied researchers to transform state-of-the-art methods into robust, production-grade systems.
* ###
Technologies:
* AI
* Cloud
* CUDA
* Docker
* Grafana
* Kubernetes
* LLM
* Machine Learning
* Prometheus
* Python
* Rust
* Serverless
* Architect
* FaaS
* Helm
More:
This is a rare opportunity to influence how next-generation LLM services are built and delivered to millions of users worldwide. You will operate at the intersection of distributed systems, high-performance computing, and AI research within a global R&D organization renowned for its resources and commitment to innovation. We are looking for an engineer who thrives on technical depth and large-scale challenges, and who is passionate about building systems that redefine possibilities in AI. If you are ready to take on one of the most impactful engineering roles available in Europe, we encourage you to apply. We are proud to be an equal opportunities employer and value diversity and inclusion in the technology sector.
last updated 50 week of 2025