C

Citi

Runs banking and payments for global clients

Low Latency Trading Infrastructure Engineer

Platform EngineeringUpdated on Nov 9
Full-timeIrving, TX, USAHybrid

About the Job

Requirements

  • The role requires 6+ years of hands-on experience in low-latency infrastructure engineering within electronic trading, capital markets, hedge funds, trading venues, or equivalent high-performance financial technology environments.
  • The candidate must have hands-on experience building and operating exchange colocation environments for equities or multi-asset electronic trading platforms, including physical rack management, cross-connect provisioning, and circuit validation.
  • The candidate must have deep technical expertise in low-latency network architecture, including ultra-low-latency switching platforms, multicast market data distribution, and Precision Time Protocol implementation and synchronization.
  • The candidate must have advanced Linux systems engineering proficiency in Red Hat Enterprise Linux or equivalent distributions, including hands-on experience in kernel tuning, CPU pinning and isolation, NUMA optimization, interrupt affinity, C-state and P-state management, and huge-page configuration.
  • The candidate must have hands-on experience with kernel bypass and packet acceleration technologies, including DPDK, XDP, Solarflare OpenOnload, and FPGA-based NIC solutions, and be able to reduce stack-level latency to sub-microsecond levels.
  • The candidate must be proficient in scripting and automation using Python, Bash, or equivalent languages, and have experience building tooling for benchmarking, telemetry collection, and infrastructure provisioning in air-gapped or tightly controlled environments.
  • The candidate must have strong experience with Ansible, Terraform, or Puppet for bare-metal provisioning, firmware management, and repeatable deployment pipelines in trading-sensitive environments.
  • The candidate must have hands-on experience designing and executing CI/CD pipelines using Jenkins, GitLab CI/CD, GitHub Actions, or ArgoCD, including build, test, and deployment automation for infrastructure-as-code workflows.
  • The candidate must have experience with container orchestration platforms including Kubernetes, including deployment, scaling, node-affinity configuration, and low-latency workload scheduling.
  • The candidate must be proficient with InfiniBand, RDMA over Converged Ethernet, and multicast networking, applied to market-data distribution and inter-system communication.
  • The candidate must have experience with low-level telemetry and monitoring tools, including packet-capture analysis tools such as Wireshark and tcpdump, hardware performance counters, and latency measurement frameworks relevant to tick-to-trade profiling.
  • The candidate must understand modern low-latency hardware platforms, NICs, and FPGA-enabled compute environments, and have experience evaluating and benchmarking hardware from vendors including Dell, HPE, Mellanox/NVIDIA Networking, Arista, Cisco, and Juniper.
  • The candidate must be familiar with exchange connectivity rules, CAT regulatory requirements, MiFID II time-synchronization standards, and internal change-control and compliance frameworks as they apply to trading infrastructure.
  • The candidate must maintain meticulous documentation and have strong written communication skills for change requests, incident reports, and certification approval packages.
  • The candidate must have experience supporting hardware procurement, vendor coordination, colocation buildouts, and telecom processes in a financial-services context.
  • A bachelor's degree in Computer Science, Electrical Engineering, Information Technology, or a related technical discipline is required, or equivalent practical experience in a highly specialized low-latency or high-performance computing environment.

Responsibilities

  • Design low-latency compute topologies using bare-metal servers, NICs, kernel-bypass technologies such as DPDK and Solarflare, and FPGA and colocation hardware.
  • Evaluate CPU microarchitecture, NUMA topology, cache behavior, and memory-bandwidth characteristics for trading workloads.
  • Define hardware and firmware standards in partnership with vendors including Dell, HPE, Mellanox/NVIDIA Networking, Arista, Cisco, and Juniper.
  • Design and maintain custom server-build patterns tailored to the low-latency trading platform and distinct from the standard enterprise server catalog.
  • Establish and enforce standards for low-latency Linux, Windows, and microservice infrastructure, including operating-system optimization, kernel-bypass technologies, CPU isolation, NUMA optimization, interrupt tuning, and deterministic performance engineering.
  • Build repeatable benchmarking harnesses to measure tick-to-trade latency, jitter, and throughput.
  • Conduct comparative hardware, firmware, and BIOS-tuning analysis, including CPU pinning, IRQ affinity, C-state and P-state tuning, and huge-page configuration.
  • Correlate benchmark results with real trading telemetry to validate production readiness.
  • Drive packet-capture analysis and latency telemetry across the full trading stack.
  • Architect and deliver high-performance colocation environments connecting exchange venues, market-data providers, and internal trading systems.
  • Implement ultra-low-latency Layer 1 and Layer 2 network configurations across trading infrastructure.
  • Execute formal certification test plans for new hardware, firmware, and operating-system or kernel builds before production introduction.
  • Maintain audit-ready certification documentation aligned with internal risk and compliance standards.
  • Coordinate with Risk, InfoSec, and exchange or venue technical teams when colocation or vendor certification is required, including compliance with CAT and MiFID II requirements for time synchronization, monitoring, and reporting.
  • Execute infrastructure provisioning and deployments within air-gapped or network-segmented environments with no direct internet access.
  • Manage image and firmware distribution using approved offline or tightly controlled transfer mechanisms.
  • Apply strict change-management and rollback procedures due to the production sensitivity of the environment.
  • Deploy and support connectivity circuits to external clients and exchanges, including cross-connect provisioning and handoff validation at specialized and colocated data centers.
  • Lead bare-metal automation, deployment pipelines, and infrastructure-as-code practices using tools such as Ansible, Terraform, and Puppet for rapid, repeatable infrastructure delivery.
  • Manage and configure Active Directory, ISA, DNS, PTP, remote-access solutions, and infrastructure management and monitoring technologies such as Lenovo LXCA, HPE OneView, Dell OpenManage Enterprise, and HCL BigFix.
  • Monitor compute health, latency drift, and hardware degradation using specialized low-level telemetry tools.
  • Manage hardware lifecycle refresh planning, including hardware aging, end-of-life firmware tracking, and vendor support contract coordination.
  • Troubleshoot at the hardware, operating-system, and network-stack levels under time-sensitive, high-impact conditions, often during live market hours.
  • Manage Kubernetes cluster operations and workload orchestration for trading-adjacent microservice infrastructure.
  • Implement and maintain high-speed interconnects including InfiniBand, RDMA over Converged Ethernet, and multicast networking protocols.
  • Collaborate with application development and support teams to optimize end-to-end trading latency and infrastructure determinism.
  • Participate in incident management and infrastructure resiliency efforts for mission-critical trading environments, including structured post-incident documentation and root-cause analysis.
  • Maintain close partnership with software delivery teams, enterprise technology groups, and trading functions throughout the end-to-end platform delivery and deployment lifecycle.
  • Produce documentation for audit and regulatory review, including change requests, incident reports, and certification approval packages.
  • Represent engineering requirements and infrastructure risk clearly in written communications to cross-functional partners in Risk, InfoSec, and Compliance.
  • Work with vendor partners, exchange providers, hardware manufacturers, and colocation data-center facility operators to optimize resiliency and performance.
  • Support hardware procurement, vendor engagement, colocation buildout activities, and telecom contract processes as an individual technical contributor.
  • Support off-hours maintenance windows and rapid incident response during market-critical periods.

Desired Qualifications

  • Experience with OpenShift or Amazon EKS is preferred.

About the Company

Citi

Runs banking and payments for global clients

Citi runs banking, investment and payment services for companies, governments and individuals around the world. Its global network connects institutions with local banking systems, while its US consumer business sells credit cards and deposit accounts. Corporate clients use Citi to manage cash, finance trade and raise capital, and investors use its trading, custody and wealth services to hold and manage assets. The bank earns interest on loans and fees from payments, securities transactions, financial advice and account services. Citi traces its banking roots to 1812; the Citigroup holding company was formed in 1998, and its headquarters are in New York City.

Company size
10,001+
Company stage
IPO
Headquarters
New York City, New York
Founded
1812

Recently Posted Jobs

Explore more opportunities at Citi

See more jobs