HPC Platform Engineer Linux - Trading

Client Server

Greater London

Hybrid

GBP 117,000 - 143,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Salary up to £130k

Pension

25 days holiday

Opportunity to work on Greenfield systems

Continual learning and development opportunities

Job summary

A global systematic trading firm is seeking an HPC Platform Engineer to develop and optimize workload scheduling solutions in HPC environments. You will work on both on-premise and cloud (AWS) platforms, collaborating with teams to enhance performance and resilience of compute infrastructures. Ideal candidates will have a strong background in Linux and HPC schedulers. Salary up to £130k with attractive benefits including bonus potential. Join a team at the cutting edge of technology in London.

Qualifications

Experience engineering and supporting HPC schedulers such as YellowDog.
Deep knowledge of Linux required.
Experience with large-scale systems with 5000+ nodes and 100k+ tasks.
Knowledge of AWS IAM and identity providers like Okta.

Responsibilities

Develop and support scalable workload scheduling solutions for HPC environments.
Collaborate with internal teams to optimize HPC platforms.
Contribute to continuous improvement initiatives and automate processes.

Skills

Experience with HPC schedulers (e.g., YellowDog, Ray, Slurm, IBM Symphony)

Deep knowledge of Linux

Understanding of loosely and tightly coupled HPC workloads

Experience with large-scale systems

Monitoring and visualization of large-scale systems

Performance tuning of compute, network and storage

Knowledge of AWS cloud services

Automation and coding in Python

Strong analysis and problem-solving skills

Collaborative and pragmatic communication skills

Education

Degree in relevant discipline (MSc/PhD level likely)

Job description

HPC Platform Engineer (Linux) London to £130k

Do you have a deep knowledge of Linux combined with HPC scheduling experience?

You could be progressing your career in a hands‑on role at a global systematic trading firm with $25 billion under management, earning significant bonuses.

Responsibilities

As a HPC Platform Engineer you’ll develop and support scalable workload scheduling solutions for HPC environments using tools such as YellowDog within a large‑scale computing environment with both on‑premise and cloud (AWS) based services. You’ll collaborate with internal teams to optimise HPC platforms, with a focus on improving performance, resilience and observability of the compute infrastructure.

You’ll also contribute to continuous improvements initiatives, automating wherever possible and sharing your expertise with the team.

Location / WFH

You’ll join colleagues based in high‑spec offices with free breakfast and lunch at the onsite restaurant, with flexibility to work from home 1‑2 days a week.

About you

You have experience of engineering and supporting at least one HPC scheduler, such as YellowDog, Ray, Slurm or IBM Symphony
You have a deep knowledge of Linux
You have a good understanding of both loosely coupled and tightly coupled HPC workloads and experience of working on large‑scale systems with 5000+ nodes and high levels of concurrency (100k+ tasks)
You have experience of monitoring and visualisation of large‑scale systems
You have experience with performance tuning of compute, network and storage components and a good understanding of the challenges of user authorisation in large‑scale distributed environments using AWS IAM and identity providers such as Okta
You have a good knowledge of AWS cloud services
You believe in automating if possible and code with Python
You have strong analysis and problem‑solving skills
You’re collaborative and pragmatic with great communication skills
You’re degree educated in a relevant discipline (likely to have studied to MSc / PhD level)

What's in it for you