Low Latency Linux Engineer

Low Latency Linux Engineer

Department: Infrastructure

Employment Type: Permanent

Location: London

Description

We are seeking an exceptional Low Latency Linux Engineer to optimize our global low-latency trading infrastructure . This is a high-impact role where your engineering choices will have a direct and measurable effect on trading performance, execution quality, and overall profitability .

You will combine hands-on technical depth with a strategic approach to system, network, and market data performance tuning . Working alongside world-class developers, quants, and platform engineers, you'll design, deploy, and refine deterministic, microsecond-level systems that underpin our trading platforms.

This is far from a traditional sysadmin position - it's a role for exceptional engineers immersed in the Linux ecosystem, who thrive on tackling kernel-level challenges, pushing bare-metal systems to their limits, and writing performance-critical code. You'll engineer and refine the RHEL platform that drives ultra-low-latency trading, addressing intricate problems in CPU scheduling, memory architecture, kernel bypass techniques, and performance-aware virtualization. Some investigations may take weeks or months to solve - this role demands persistence, precision, and a genuine passion for performance engineering .

Key Responsibilities
• OS Engineering & Tuning: Customize and refine RHEL for high-performance, low-latency workloads, including kernel parameters, IRQ handling, CPU pinning, NUMA optimization and memory management.
• Kernel Bypass & User-Space Networking: Implement and optimize technologies such as Solarflare OpenOnload/TCPDirect/ef_vi , DPDK, InfiniBand verbs, or Exablaze to minimize network stack latency.
• Bare-Metal Performance: Tune BIOS/firmware; optimize CPU scheduling, cache utilization, and pipeline efficiency for deterministic execution.
• High-Performance Storage: Deploy and fine-tune NVMe over RoCE for ultra-fast data access in trading environments.
• Precision Timing: Manage and optimise PTP across the estate.
• Observability & Diagnostics: Build and enhance monitoring and alerting and implement a packet capture solution for latency analysis.
• Coding & Debugging: Write and maintain high-performance tooling in Java, Python, or Golang to support infrastructure performance, profiling, and automation.
• Cross-Team Collaboration: Partner with quants, network engineers and platform engineers to integrate performance enhancements into trading platforms.

Skills, Knowledge and Expertise
• Proven RHEL/Linux performance engineering expertise in ultra-low-latency environments.
• Strong programming skills in Java , Python , or Golang , with ability to debug at system and kernel levels.
• Experience with hardware performance counters , profiling tools, and in-depth performance analysis.
• Deep knowledge of modern CPU architectures (Intel & AMD), including cache hierarchies and NUMA considerations.
• Hands-on experience with kernel-bypass frameworks (Solarflare OpenOnload/TCPDirect/ef_vi, DPDK, InfiniBand verbs, Exablaze).
• Understanding of managed runtime performance challenges (Java, C#) and mitigation strategies.
• Understanding of FIX protocol and multicast messaging concepts.
• Familiarity with PTP timing solutions and packet capture analysis.
• Designing and implementing automation solutions using Infrastructure as Code (IaC) tools such as Ansible, Python, and Terraform to streamline and standardize operational workflows.

Personal Attributes
• Clear communication - explains technical concepts concisely and effectively
• Adaptability - adjusts to new technologies and unexpected challenges
• Analytical thinking - breaks down complex issues logically and methodically
• Decision-making - balances speed and accuracy when making technical decisions
• Collaboration over competition - prioritises team success over individual wins
• Accountability - follows through on commitments and owns mistakes
• Patience - supports teammates as they learn or troubleshoot issues
• Open to feedback - accepts and applies suggestions for improvement
• Growth mindset - always looks for ways to improve skills and workflows
• Proactiveness - takes initiative instead of waiting for instructions