Senior AI Compute Infra Engineer — GPU-Driven, Scalable in Katowice

Kraken is building a dedicated AI Compute and Infrastructure team to power model training, inference and evaluation. You will own GPU clusters, design scalable infrastructure, and partner with ML researchers to ensure fast, reliable, and cost-efficient AI workloads. You will work with vLLM, Triton, TensorRT, TorchServe, KServe, and Ray Serve, helping to reduce external dependencies while maintaining production-grade stability and observability. This is a high-impact, always-on environment.