Summary
Thomas Bourcey is an experienced HPC Delivery Engineer with 16 years of expertise designing, deploying and operating large-scale high-performance computing clusters, massive tape-based HPSS storage (up to ~1.2 Exa), and observability stacks across international, critical environments. Based in Toulouse, he combines deep Linux/storage/virtualization skills (NetApp, GPFS, Lustre, InfiniBand) with DevSecOps and automation using Ansible, Bash, Python and Go to deliver reproducible, automated infrastructures for up to 2000+ node clusters. As a tech lead he architects monitoring and alerting platforms (Prometheus, Grafana, Thanos, Loki), builds custom exporters and drives delivery best practices while contributing to open-source tooling. His background includes system architecture, NetApp and MetroCluster projects, HPC workload managers (Slurm, PBS), and cloud/Kubernetes transformations, giving him a rare blend of tape-scale storage operations and modern cloud-native observability. Not obvious from the title: he routinely operates at the intersection of aerospace-grade engineering workflows and large-scale scientific computing, translating domain-specific toolchains into production-grade HPC services.
16 years of coding experience
BTS, Informatique de Gestion, BTS, Informatique de Gestion at ADRAR Formation
French, English