Member of Technical Staff: AI Systems Engineer

Job Description

As a core member of the technical staff, you will architect and optimize high-throughput inference systems for large-scale generative models. You will tackle deep technical challenges in distributed systems and hardware-software co-design, directly impacting the latency and scalability of production-grade AI services for a global developer ecosystem.

Location

London, UK

Why this role is remarkable

• Work at the intersection of systems engineering and cutting-edge machine learning research to define the future of model deployment.
• Join an elite technical team backed by top-tier venture capital firms during a period of rapid infrastructure scaling.
• Influence the foundational layer of AI applications by building systems that make massive models commercially viable and performant.

What You Will Do

• Design and implement low-level optimizations for model inference to maximize GPU utilization and minimize token latency.
• Build robust, distributed systems capable of serving frontier models with high reliability and cost-efficiency.
• Collaborate with research teams to integrate novel architectures into production-ready inference engines and serving stacks.

The ideal candidate

• Demonstrates deep expertise in systems programming and optimizing performance-critical software in C++ or Rust.
• Has a proven track record of working with deep learning frameworks and low-level GPU acceleration libraries.
• Possesses a strong understanding of distributed systems and the mechanics of modern large language model architectures.