Scalable LLM Infrastructure Engineer

United States Digital Space LLC; Greater London; On-site; GBP 89,000 - 134,000; Full time

Job summary

United States Digital Space LLC is seeking a Software Engineer on the ML Infrastructure team to design and build scalable backend platforms for serving LLMs in research and production contexts.

You will collaborate with researchers and engineers, lead end-to-end projects, and implement monitoring and deployment tooling using Docker, Kubernetes, and cloud IaC. 4+ years of backend experience and proficiency in Python/Go/Rust/C++ are preferred.

Qualifications

• 4+ years of experience building large-scale backend systems.
• Strong programming skills in Python, Go, Rust or C++.
• Experience with LLM serving, routing and model optimization concepts.
• Familiarity with containers, orchestration, and cloud infrastructure.
• Ability to work independently in a fast-moving environment.

Responsibilities

• Build and maintain fault-tolerant, high-performance systems for serving LLMs at scale.
• Create internal platforms to enable LLM capability discovery.
• Collaborate with researchers and engineers to productionize models.
• Lead architecture reviews and drive implementation end-to-end.
• Develop monitoring and observability to ensure system health.

Skills

Backend systems

Python

Go

Rust

C++

LLM serving

Distributed systems

Tools

Docker

Kubernetes

AWS

GCP

Terraform

Job description

United States Digital Space LLC is seeking a Software Engineer on the ML Infrastructure team to design and build scalable backend platforms for serving LLMs in research and production contexts.

You will collaborate with researchers and engineers, lead end-to-end projects, and implement monitoring and deployment tooling using Docker, Kubernetes, and cloud IaC. 4+ years of backend experience and proficiency in Python/Go/Rust/C++ are preferred.