Jobs, fresher vacancy - HPC Architect • UK

Company: Selby Jennings London

UK

A leading global investment firm is seeking an experienced HPC Architect to design and optimise high-performance computing (HPC) infrastructure. This role involves building scalable, high-efficiency solutions that support cutting-edge quantitative and systematic trading strategies. The ideal candidate will have deep expertise in infrastructure design, performance tuning, and enterprise-level computing environments. Role Overview:The HPC Architect will focus on research, design, implementation, and Level 3 support for the firm's advanced HPC systems. The role requires close collaboration with engineers, developers, quants, and external vendors to enhance compute performance, scalability, and reliability. The successful candidate will be comfortable operating in a fast-moving, high-stakes environment, applying technical expertise to solve complex infrastructure challenges. Key Responsibilities: Architect, document, and optimise core platform components, including compute, storage, and cloud environments. Implement and refine HPC solutions utilising modern computing architectures such as GPUs, high-speed interconnects, and next-generation CPUs. Analyse resource utilisation and implement strategies to optimise compute and storage efficiency. Develop detailed technical documentation and best practices for system design and troubleshooting. Manage project life cycles, collaborating with internal teams and external partners. Provide Level 3 escalation support for critical infrastructure incidents and performance issues. Adapt solutions to evolving business and technological requirements. Required Qualifications: 10+ years of experience working with Linux (RHEL, Rocky, CentOS, or OEL preferred) in large-scale enterprise or HPC environments. Expertise in fine-tuning system performance (memory, CPU, networking) for high-throughput computing. Strong ability to diagnose and resolve low-level performance issues at the OS, software, storage, or network level. Knowledge of server architecture, including key differences between Intel, AMD, and ARM chipsets, and when to use each. Hands-on experience with HPC job schedulers such as Slurm, RunAI, or Bright Cluster Manager. Proficiency in Python and/or C++ for automation, scripting, and debugging. Highly organised, adaptable, and comfortable in fast-paced, dynamic environments. Strong analytical thinking and problem-solving skills for diagnosing obscure technical issues. Bachelor's degree in computer science, Engineering, or a related field. Preferred Qualifications: Experience with automation/configuration management tools (Ansible, Chef, Terraform). Familiarity with different network switch vendors and architectures. Experience with time-series databases such as KDB/Q. Ability to debug and enhance applications using frameworks like XGBoost, LightGBM, PyTorch, or TensorFlow. Knowledge of Kubernetes and how to integrate HPC workloads into containerised environments.