Latest AI JobsBrowse Jobs
Kraken logo

Senior AI Compute Infrastructure Engineer

KrakenUnited KingdomEngineering
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Posted
7 May 2026
Status
Open · checked 7d ago

About this role

The Senior AI Compute Infrastructure Engineer position at Kraken is a remote role based in the United Kingdom within the engineering department. This opportunity suits an experienced infrastructure professional who wants to design, scale, and optimize the underlying GPU compute architecture powering advanced artificial intelligence and machine learning workloads.

Role Overview

Kraken is establishing a dedicated AI Compute and Infrastructure team to support the next generation of model training, inference, and experimentation. Operating within engineering leadership, the selected candidate will own the infrastructure layer that enables reliable, cost-efficient, and secure AI workloads at scale. Working alongside machine learning researchers, security teams, and platform engineers, this role focuses on building production-grade compute systems that handle complex model serving and accelerator clusters.

Key Responsibilities

Operate and manage GPU and accelerator clusters used for model training, inference, evaluation, and experimentation, covering drivers, runtimes, node configurations, and workload isolation.
Design local infrastructure solutions that reduce dependency on external providers and efficiently manage compute expenditures.
Improve orchestration, scheduling, quota management, and placement systems across varied accelerator environments.
Optimize inference pipelines for memory efficiency, throughput, latency, reliability, and cost using advanced serving stacks.
Collaborate with machine learning engineers to eliminate performance bottlenecks throughout the training, evaluation, and deployment phases.
Establish comprehensive observability frameworks tracking GPU utilization, memory pressure, token throughput, request latency, and queue depth.
Drive reliability standards through effective incident response, runbooks, alerting, and post-incident reviews.
Evaluate and integrate new hardware, specialized accelerators, cloud instance families, and scheduling frameworks.
Develop internal tooling to make GPU consumption transparent and accessible to other teams without requiring infrastructure expertise.

Requirements

Five or more years of infrastructure engineering experience focusing on GPU compute, distributed systems, machine learning infrastructure, or high-performance computing.
Practical background in operating production-grade GPU clusters or accelerator-backed environments.
Strong systems engineering fundamentals encompassing Linux, networking, storage, containers, and Kubernetes.
Familiarity with machine learning serving frameworks such as Triton Inference Server, vLLM, TensorRT, or KServe.
Proficiency in Python for infrastructure automation, operational workflows, and debugging.
Understanding of performance metrics across concurrency, memory usage, batching, GPU utilization, and throughput.
Track record of balancing performance, availability, and cost efficiency in large-scale environments.

Nice to Have

Experience working at a hyperscaler, frontier AI lab, high-frequency trading firm, or large-scale machine learning organization.
Familiarity with specialized accelerators or custom silicon like AWS Trainium, TPUs, or Gaudi.
Background in capacity planning, fleet cost management, or reserved capacity strategy.
Exposure to distributed training frameworks including Megatron-LM, DeepSpeed, FSDP, or Ray.
Low-level debugging skills for CUDA, NCCL, memory, drivers, or runtime issues.
Proficiency in systems languages such as Rust, C++, or Go.
Background in crypto, financial services, or security-sensitive infrastructure.

Skills and Tools

Python
AWS
Kubernetes
Rust
C++
Linux
Triton Inference Server
vLLM
TensorRT

About the Company

Founded in 2011, Kraken operates as a globally recognized digital asset platform serving millions of clients with spot trading, futures, margin, staking, and over-the-counter services. Payward, the parent company, supports a portfolio of modern financial infrastructure platforms designed to advance an open and accessible financial system worldwide.

How to Apply

Interested candidates should visit the official Kraken careers page to submit an application for this remote position.

Skills and tech stack

PythonAWSKubernetesRustC++

Questions candidates ask

Where is the Senior AI Compute Infrastructure Engineer position located?

This position is remote with a location designation of the United Kingdom.

What department does this role belong to?

The role sits within the engineering department under the dedicated AI Compute and Infrastructure team.

What level of experience is required for this role?

Applicants need 5 or more years of infrastructure engineering experience, with significant focus on GPU compute, distributed systems, or machine learning infrastructure.

What programming languages and tools are relevant to this job?

Key technologies include Python, AWS, Kubernetes, Rust, C++, Linux, and serving frameworks such as vLLM and Triton Inference Server.

How can I apply for this position?

Candidates can apply directly through the official Kraken careers website.

Ready to apply?

The application is on the official Kraken careers page.

Apply on company site