High-Performance Systems Engineer – Compute & Networking

Referment; Greater London; On-site; GBP 70,000 - 110,000; Full time

Job summary

Referment is partnering with a global investment and technology organisation to hire a Systems Developer. The role focuses on hands‑on engineering across large‑scale compute, OS internals, tooling, networking and storage.

You will design, implement and tune workload scheduling, fleet management and clustered file systems, while building metrics tools to measure performance. The job suits engineers who enjoy OS-level work and high‑throughput, low-latency infrastructure in a distributed team.

Qualifications

• Experience with infrastructure orchestration and fleet management.
• Advanced Python proficiency for systems engineering, including high‑concurrency frameworks like FastAPI or asyncio.
• Degree in Physics, Mathematics, Computer Science or related field, or up to five years of practical experience.

Responsibilities

• Design and improve workload scheduling and fleet-management for large compute environments.
• Contribute to clustered file-system design, tooling and platform reliability.
• Investigate and tune kernel and network performance for latency-sensitive apps.
• Build metrics collection and analysis tools to understand and improve infrastructure behaviour.
• Collaborate with a global engineering team supporting research and trading workloads.

Skills

infra orchestration

fleet management

Python

FastAPI

Asyncio

high-concurrency

communication

Education

Physics/Mathematics/CS degree

Tools

Ansible IaC

OCI REST APIs

Linux networking

Job description

Referment is partnering with a global investment and technology organisation to hire a Systems Developer. The role focuses on hands‑on engineering across large‑scale compute, OS internals, tooling, networking and storage.

You will design, implement and tune workload scheduling, fleet management and clustered file systems, while building metrics tools to measure performance. The job suits engineers who enjoy OS-level work and high‑throughput, low-latency infrastructure in a distributed team.