Research Technology Developer in City of London

Overview

XTX Markets is a research-driven organisation built and led by mathematicians and computer scientists. The Research Technology team sits at the heart of the company; the HPC cluster is a core asset, and driving its development is a primary focus. The firm trades globally with daily volumes of over $250bn per day. The cluster is one of the largest HPC clusters in the world, built by the team to meet scale and reliability needs beyond standard software. The team collaborates with researchers to create a performant, reliable, and transparent system. The role is a senior software development position within the Research Technology team, focusing on the software that powers the HPC cluster.

What we are doing:

• We are building an exa-scale filesystem designed to handle billions of directories, a trillion files, and a million clients across multiple datacentres, with complete resiliency against hardware failure. Our job scheduler operates on a dynamic graph of over 10 million entries, managing the concurrent operation of 100k tasks. We are building zero-touch platforms for monitoring, operation, and upgrade of tens of thousands of machines, integrating with DC-ops teams.
• We build our own file formats, compression algorithms, and custom GPU tooling and network management software to optimise performance from 20,000 high-end GPUs.
• We plan to open the cluster to more teams and expand across multiple datacentres.
• We aim to improve measurement and optimisation of resource usage across the entire cluster to enhance performance.
• Exceptional candidates will be involved in low-level software design interfacing with GPU/CPU, including filesystem and network drivers and computational algorithms.

Responsibilities

The Research Technology team is responsible for all aspects of the firm’s HPC cluster and supporting the work of quantitative researchers who use it. This role is primarily focused on software development within a full-stack team that collaborates with researchers to deliver reliable, scalable systems.

• Self-motivated, proactive engineers who mentor junior team members and push the team to achieve more.
• Engage constructively with researchers and seek novel, scalable problem-solving approaches.
• Strong awareness of risk; able to drive radical change in a pragmatic, secure manner to reduce operational risk.
• Able to work in a fast-moving environment and maintain a complex live system 24/7, delivering changes on tight deadlines.
• Solid grounding in academic CS fundamentals (algorithms and data structures).
• Proficient in at least one statically typed language; Golang and Rust experience is helpful, Python for scripting.
• Approximately 5-10 years of experience designing and building large-scale distributed systems.
• Strong problem-solving and analytical skills.
• Familiarity with Linux; ability to diagnose performance and scalability issues.
• Ability to multi-task across multiple projects and prioritise effectively.
• Highly self-motivated and capable of working independently.
• Understanding of one or more machine learning frameworks and compute offload devices (GPUs) is advantageous.

Benefits

• Onsite gym, sauna, and fitness classes at no charge
• Extensive medical benefits including an on-site doctor and therapist at no charge
• Breakfast and lunch provided Monday to Thursday
• Support for caregivers, including emergency dependent care
• Beautiful Kings Cross office
• 25 days paid holiday per year plus statutory holidays and paid sick days. We currently operate 4 days a week in-office, 1 day from home.

Please describe the most complex, high-scale system you have worked on, and what your role was. *

Please briefly highlight why you have applied for this role specifically at XTX. Please note this role does not interface with trading or trading systems. *