Senior AI Compute Infrastructure Engineer

About the role

Payward is building a dedicated AI Compute and Infrastructure team to power the next generation of model training, inference, evaluation, and experimentation for Kraken. As a Senior AI Compute Infrastructure Engineer you will design, operate, and optimise GPU and accelerator clusters that enable fast, reliable, and cost‑efficient AI workloads across the exchange.

Key responsibilities

• Own and operate GPU and accelerator clusters, including drivers, runtimes, kernels, device plugins, node configuration and workload isolation.
• Design infrastructure that allows teams to run models locally on GPUs, reducing reliance on external providers.
• Build and improve scheduling, orchestration, placement, quota management and utilisation systems for heterogeneous accelerator environments.
• Optimise inference pipelines for latency, throughput and cost using frameworks such as vLLM, Triton Inference Server or TensorRT.
• Partner with ML engineers and researchers to remove bottlenecks in training, batch and online inference, deployment and debugging.
• Develop observability for GPU utilisation, memory pressure, queue depth, token throughput, request latency and spend.
• Drive reliability through incident response, alerting, runbooks and post‑incident improvements.

Required profile

• Senior‑level engineer with a strong background in building production‑grade compute infrastructure.
• Experience working closely with AI/ML researchers, platform engineers, security and product teams.
• Proven ability to deliver fast, dependable and cost‑effective solutions at scale.

Required skills

• GPU and accelerator cluster management
• Linux drivers, runtimes and kernel configuration
• Device plugins and workload isolation techniques
• Scheduling, orchestration and quota management
• vLLM, Triton Inference Server, TensorRT or equivalent serving stacks
• Model serving and inference pipeline optimisation
• Observability and monitoring of GPU utilisation and performance metrics