HPC Network Engineer

Hudson River Trading’s High Performance Computing (HPC) Network Engineering team designs and engineers the low-latency communications infrastructure that underpins our incredibly large GPU and CPU compute clusters. Our mandate is to architect, optimize, and scale the high-performance LAN and WAN infrastructure that interconnects globally distributed, large-scale on-prem data centers, enabling them to grow rapidly and operate at peak performance in support of HRT’s demanding computational workloads.

We are looking for a Network Engineer with deep experience in designing, deploying, and scaling networks for large-scale HPC environments. You will be building the next generation of infrastructure required by a premier algorithmic trading firm operating at the forefront of technology and finance.

This position requires deep technical skills, along with the  product leadership and vision needed for the future of cloud-scale networking. You’ll have broad responsibilities and freedom to analyze and solve problems, and your solutions will have an immediate impact on our operations worldwide. We’re looking for someone who loves  technology and is excited about tackling big picture problems. You will work on a wide variety of projects to enhance the performance and capacity of the network and contribute to both the management and the technical nitty-gritty of our computing architecture.

Our people and our compute capabilities are our two most important differentiators, and that is where we are investing the most.

Responsibilities Network design, product selection, routing, configuration and troubleshooting

Closely work with our HPC Systems team, as well as other teams to scale our research environment Meet with external parties for project related items as well as future endeavors

Overall capacity planning for the data center networks

Develop scripts and processes to increase efficiency

Collaborate with others in the network team to solve cross discipline problems

Provide detailed documentation Mentor others as a senior resource Profile
10+ years of relevant experience

Proven ability to prioritize workloads and manage implementation schedules with a meticulous attention to detail Proactive problem-solver with the technical skills and hands-on mentality to tackle challenges in the field.

Strong collaboration skills and a focus on continuous improvement, with the humility to own and learn from mistakes Skills Excellent oral and written communication skills: able to distill complicated issues into clear and concise terms

Able to create and maintain clear and effective technical documentation

In depth understanding of common layer 2 and layer 3 network protocols (OSPF, BGP, PIM, IGMP, RoCEv2, spine-leaf architecture, and VXLAN) and best practices for them Proven ability to select and work with vendors to engineer switches for next-generation computing environments

Experience managing Arista (EOS), Cisco (NX-OS), Nvidia (Cumulus) and SONiC-based switches, as well as an interest in exploring new platforms

Strong design skills in computing and grid networks, with expertise in capacity planning, and full lifecycle project management

Experience with packet decoding and analysis tools such as tcpdump and Wireshark

Experience with public cloud networks, such as AWS, GCP, Azure Familiarity with configuration management tools, such as Ansible or Salt is desirable to support zero-touch network management

Familiarity with Python, Prometheus, Grafana, ELK, Git Hub is desirable

Understanding of basic power consumption and cooling issues in a data center environment

Knowledge of fiber optics technology and cabling standards ranging from 1 to 800 Gbps. Ability to sort through specs and make recommendations on appropriate…