Linux Systems Engineer - Latency Critical Trading Technology
Latency Critical Trading (LCT) seeks a Linux Systems Engineer to join our infrastructure team.
The LCT Team is responsible for delivering high quality, low-latency trading capabilities for Millennium's businesses by delivering a world class Linux platform and the support to match. The ideal candidate should be a confident communicator with hands-on experience in a Linux environment and the ability to contribute to platform development and day to day support. A passion for Linux system internals and tracing through complex issues to arrive at a resolution will serve our ideal candidate well.
Team Composition
Our team consists of highly skilled Linux, Network, SRE, and software engineers equipped with the tools and untethered access required to make meaningful changes to both general purpose and niche server environments. We pride ourselves in providing a stable and high performing platform to our users which include portfolio managers, researchers, and other technologists. A great deal of focus is spent on continuously learning, consistently making improvements, and building a cohesive team.
Job Function Summary
As a member of LCT's Linux infrastructure team, the candidate will work closely with application developers and portfolio managers to understand and translate business requirements into technical deliverables. The candidate will be expected to communicate effectively with a global team to handle requests and incidents from various high-profile clients, as well as participate in driving or contributing to building the team's configuration management system using Ansible and Python. Knowledge of kernel bypass technologies, and general latency and performance tuning practices would be helpful in this role, but are not strictly required.
Principal Responsibilities
Part of the globally distributed engineering team that supports and maintains the firm's trading-oriented Linux stack
Strong sense of task and mission ownership, ability to serve as a bridge between regions
Participates in regular troubleshoots around issues such as packet loss, high latency, instability, etc.
Proactively working to understand our internal clients' needs, communicating them effectively to leadership both regionally and globally
Identifying risks, forming contingency plans, and implementing them
Monitoring the performance and health of the latency critical computing environment
Driving or assisting in troubleshooting advanced system/network issues involving kernel bypass, complex routing and switching schemes, multicast protocols, and precision timing systems
Participating in occasional (monthly) on-call responsibilities, and assisting the oncalls during their shifts
A desire to learn and grow skillsets both independently and from other senior team members, and maintain training materials and documentation for others
Qualifications/Skills Required
Excellent ability to communicate respectfully and professionally with individuals and teams at varying levels of seniority from Intern to Senior Portfolio Manager
An outgoing, positive attitude when facing off towards clients and management during incidents
Strong grasp of Linux system internals, kernel operations, memory management, sockets, interrupts, etc
Fundamental (or better) knowledge of kernel bypass (e.g. Onload, VMA, etc) technologies and why they exist
Solid understanding of basic network protocols (TCP/IP, UDP, IGMP, etc) and how the kernel deals with them
Ability to automate manual processes using Python, Perl, or another high-performance interpreted language
Ability to automate infrastructure tasks in Ansible, or a strong desire to actively learn and participate in Ansible development
Some understanding of compiled programming languages (C/Cpp) and their dependencies
A desire to expand one's knowledge base, collaborate between areas, and contribute to building a strong and cohesive team within the region and beyond
Ability to be on-site required, occasional travel to New York may be required.
A genuine passion for making Linux go fast, and doing so consistently