eTrading Full Stack Engineering - Compute
HSBCIn compliance with applicable laws, HSBC is committed to employing only those who are authorized to work in Canada. Applicants must be legally authorized to work in Canada as HSBC will not engage in immigration sponsorship for this position. In Canada, HSBC Global Services (Canada) Limited (HGCA) is a wholly owned subsidiary of HSBC Global Services Limited. Operating in Toronto, HGCA is part of a global service company, delivering services to support the operating entities of HSBC Group. We have different capabilities that provide tools and processes to facilitate the functions, business, and entities with their service management responsibilities. Ready to build deterministic low-latency compute for electronic trading? Why HSBC HSBC is one of the largest banking and financial services organizations in the world. Guided by our purpose of opening up a world of opportunity, our ambition is to become the world’s most trusted bank globally, putting customers at the heart of everything we do. The Opportunity Join our eTrading infrastructure engineering team in Markets & Securities Services Information Technology, building deterministic, secure and highly available compute platforms supporting latency-sensitive electronic trading. This hands-on role covers bare-metal server architecture, Red Hat Enterprise Linux (RHEL), Docker and Podman, hardware lifecycle engineering, operating system security and compliance, software supply chain controls, telemetry and automated validation. You’ll work with trading, application engineering, network, security, operations, data center providers and hardware vendors to deliver repeatable, observable and performance-engineered platforms. Success means predictable low latency and minimal jitter, strong security posture and smooth lifecycle execution across hardware, firmware and operating system changes. The role has end-to-end engineering responsibility for the design, qualification, deployment and operational support of physical server platforms in co-located and enterprise data centers. What you'll be doing Translate trading workload profiles into qualified server bills of materials covering central processing unit (CPU) characteristics, non-uniform memory access (NUMA) topology, memory, storage, network interface cards (NICs) and lifecycle constraints Benchmark and certify server hardware and firmware combinations and document performance, resilience, thermal and compatibility evidence before production approval Build, patch, harden and support Red Hat Enterprise Linux (RHEL) platforms using standardized images, repositories, provisioning and controlled lifecycle processes Engineer basic input output system (BIOS), firmware, kernel and user space settings for deterministic performance including CPU isolation, interrupt request (IRQ) placement, power policy, NUMA locality and network tuning Establish repeatable baselines for latency, jitter, throughput and resource contention and detect regressions through long-running tests and controlled changes Engineer and support Docker and Podman runtimes including registries, image lifecycle, resource controls, storage and networking while preserving performance predictability and security Develop and operate OpenSCAP profiles, scans, remediation workflows, exceptions and audit evidence appropriate to RHEL trading servers Generate and govern Software Bill of Materials (SBOMs) for operating system packages, container images, drivers, firmware and platform tooling and integrate vulnerability, provenance and release policy checks into delivery pipelines Automate inventory, health, BIOS settings, firmware and lifecycle workflows through Redfish and vendor management controllers Implement observability for CPU scheduling, interrupts, NUMA, memory, storage, network, thermal state, hardware faults, containers and operating system health then investigate issues using tracing and system logs What we're looking for Bring substantial hands-on server, Linux…