Senior System Engineer; HPC Frequency Trading

The Role

Durlston Partners is working with a HFT firm in New York that is looking for a Senior HPC Engineer to architect their next-generation compute grid.

You’ll be joining a team of engineering heavyweights—think ICPC World Finalists, kernel maintainers, and former national lab researchers—operating in a relaxed, open-collar environment. This is a tech-first culture where the hardware specs matter more than the dress code. You’ll have the freedom to push metal to its absolute limit without the bureaucratic red tape of a traditional bank.

You will own the performance of the firm’s massive distributed compute environment. This is a deep systems role where you will optimise everything from the job scheduler down to the instruction set, ensuring the research team has the raw power needed to train models and simulate strategies at lightning speed.

• Architect and optimise a large-scale, high-performance computing (HPC) grid for quantitative research and simulation.
• Deep dive into Linux kernel tuning, network stack optimization (kernel bypass/Solarflare), and memory management to squeeze every cycle out of the hardware.
• Develop tooling in Python to automate cluster management, job scheduling (Slurm/Kubernetes), and resource allocation.
• Collaborate with quants to parallelise algorithms and optimise code for specific hardware architectures (AVX-512, GPU acceleration).
• evaluate and integrate cutting-edge hardware (latest CPUs, high-speed interconnects, storage solutions).

• Expert-level Linux Systems Engineering: Deep understanding of OS internals, kernel tuning, and file systems (Lustre, GPFS, or similar).
• HPC
  
  Experience:
  
  Proven track record managing large-scale grids (thousands of cores) and schedulers (Slurm, LSF, or HTCondor).
• Hardware Knowledge: Understanding of modern CPU architecture, memory hierarchy, and high-performance networking (Infiniband, RoCE).
• Problem Solving: A degree in Computer Science, Engineering, or Physics from a top university.

• A relaxed, engineering-led culture with a flat hierarchy.
• The budget to buy the absolute best hardware available on the market.
• Direct impact: your infrastructure directly determines the speed at which the firm can innovate.

If you are interested, please apply! Alternatively, feel free to reach out to for a confidential discussion.