Senior AI Compute Infrastructure Engineer

About the role

Join Kraken’s new AI Compute and Infrastructure team to build and operate high‑performance GPU and accelerator clusters that power model training, inference, evaluation, and experimentation across the exchange.

Key responsibilities

• Own and operate GPU/accelerator clusters, including drivers, runtimes, device plugins, scheduling primitives and workload isolation.
• Design and improve scheduling, orchestration, placement, quota management and utilization systems for heterogeneous accelerator environments.
• Optimize inference pipelines for latency, throughput and cost using frameworks such as vLLM, Triton Inference Server or TensorRT.
• Partner with ML researchers and engineers to remove bottlenecks in training, batch and online inference, deployment and debugging workflows.
• Build observability for GPU utilization, memory pressure, queue depth, token throughput, request latency and spend.
• Drive reliability, incident response, alerting, runbooks and post‑incident improvements for always‑on AI compute infrastructure.

Required profile

• 5+ years of infrastructure engineering experience with GPU compute, ML infrastructure or large‑scale production platforms.
• Hands‑on experience operating GPU/accelerator clusters in production, including scheduling, orchestration and cost optimisation.
• Strong systems engineering fundamentals across Linux, networking, storage, containers and Kubernetes.
• Proficiency in Python for automation, tooling and operational workflows.
• Experience with ML serving frameworks such as vLLM, Triton Inference Server, TensorRT, TorchServe, KServe or Ray Serve.

Required skills

• GPU and accelerator cluster management
• Kubernetes and container orchestration
• Linux systems administration
• Python scripting and automation
• ML serving frameworks (vLLM, Triton, TensorRT, TorchServe, KServe, Ray Serve)