Hpc Engineer
– Optimize applications on different hardware/languages (speedups 3x - 40x) ∗ C++ applications in GPUs using CUDA on Windows ∗ Scientific applications (C/C++) in CPUs using Intel vector intrinsic functions on Linux ∗ Tensorflow custom operations in GPUs using Python, CUDA, C, OpenGL on Linux ∗ C# applications in CPUs using threads (Tasks and Parallel.For) and processes on Windows– Migration of highly optimized on-premises and cloud infrastructure (Autoinstall, Cloud-init, Ansible, KVM)– Scalable Kubernetes based clusters using MinIO, NATS-streaming, FissionIO, Grafana, kubeflow, argo, and katib