Senior AI Compute Infrastructure Engineer

📋 Description

• Own and operate GPU and accelerator clusters for training, inference, and experimentation.
• Design infra to run models locally on GPUs, reducing external dependencies and costs.
• Build scheduling, orchestration, placement, quota, and utilization across heterogeneous accelerators.
• Optimize inference pipelines for latency, throughput, memory, and cost (vLLM/Triton/TensorRT).
• Partner with ML researchers to remove bottlenecks in training, evaluation, and online inference.
• Build observability for GPU usage, memory pressure, queues, latency, and spend.

🎯 Requirements

• 5+ years of infrastructure engineering experience with GPU compute, ML infra, distributed systems, HPC, or large-scale production platforms.
• Hands-on experience operating GPU clusters or accelerator-backed infra, including scheduling, orchestration, utilization monitoring, and cost optimization.
• Strong systems engineering fundamentals across Linux, networking, storage, containers, Kubernetes, distributed runtimes, and production debugging.
• Experience with ML serving frameworks such as vLLM, Triton Inference Server, TensorRT, TorchServe, KServe, Ray Serve, or equivalents.
• Proficiency in Python for infrastructure automation, tooling, debugging, integration, and operational workflows.
• Practical understanding of performance tradeoffs across batching, concurrency, memory usage, GPU utilization, latency, throughput, availability, and cost.

🎁 Benefits

• Global, merit-based culture with equal opportunity.
• Remote-friendly work with an international team.
• Opportunity to build cutting-edge AI compute infra for Kraken.
• Diverse, world-spanning Payward family.