HPC Architect: Linux Storage & Compute Leader

MBDA UK Ltd; West of England; Hybrid; GBP 45,000 - 75,000; Full time

Benefits offered by this job

Company Bonus

Pension 14%

Flexible working

Enhanced parental leave

Facilities

Healthcare plan

Job summary

MBDA UK Ltd is seeking a forward-thinking HPC Architect to define the strategic direction for storage and infrastructure across MBDA's HPC environments. The role focuses on scalable, high‑throughput systems and cross‑functional collaboration to meet evolving business needs.

You will design long‑term roadmaps, manage compute, storage and interconnects, and guide software ecosystems including SLURM, Kubernetes for HPC, MPI and CUDA. Hybrid work and security clearance are key elements of the role.

Qualifications

• Forward thinking HPC architect with expertise in storage and infrastructure.
• Able to define long-term HPC architecture roadmaps aligned with business objectives.
• Experience in managing HPC environments including compute nodes, storage and interconnects.
• Ability to collaborate with cross-functional teams across multiple sites.

Responsibilities

• Architecture & Strategy: Define the long-term HPC architecture roadmap and standards.
• System Design & Engineering Oversight: Architect large-scale HPC clusters and high‑speed networking.
• Performance & Scalability: Ensure throughput, latency and capacity planning for HPC workloads.
• Workload & Software Ecosystem: Guide workload orchestration (SLURM, Kubernetes for HPC) and software stack (MPI, CUDA, libraries).

Skills

HPC architecture

Storage expertise

Infrastructure design

SLURM

Kubernetes for HPC

MPI/CUDA

InfiniBand networking

Tools

SLURM

Kubernetes for HPC

MPI

CUDA

Job description

MBDA UK Ltd is seeking a forward-thinking HPC Architect to define the strategic direction for storage and infrastructure across MBDA's HPC environments. The role focuses on scalable, high‑throughput systems and cross‑functional collaboration to meet evolving business needs.

You will design long‑term roadmaps, manage compute, storage and interconnects, and guide software ecosystems including SLURM, Kubernetes for HPC, MPI and CUDA. Hybrid work and security clearance are key elements of the role.