London, South East, England, United Kingdom Hybrid / WFH Options
Octad Recruitment Ltd
Desirable skills: Experience in solving non-linear least square problems Experience with Computer Vision Experience in UI development e.g. ImGui Understanding of multithreading techniques Experience with GPU programming e.g. CUDA Experience with a messaging framework, e.g. NATS, RabbitMQ Experience working in and configuring cloud environments (e.g. AWS, Azure, GCP) Experience working with software containers (Docker, Podman) and container orchestration More ❯
or create insights, that's a plus. Deeper systems knowledge. Extraexperience with any of the following would be an asset: developing GPU kernels and/or ML compilers (e.g. CUDA, OpenCL, TensorRT Plugins, MLIR, TVM, etc); optimizing systems to meet strict utilization and latency requirements with tools such as Nvidia NSight; and/or you've worked with embedded More ❯
scientists, and how to optimize the experience Core Technical skills : System administration experience with OS's like RHEL/CentOS, Ubuntu, tuning Linux kernel Proficiency with Ansible, Nvidia and CUDA toolkits, Kubernetes and container orchestration Understanding of automation, monitoring and security with GPU as a service Preferred experience Experience supporting HPE PCAI or other AI/HPC infrastructure and More ❯
scientists , and how to optimize the experience. Core Technical skills: System administration experience with OS's like RHEL/CentOS, Ubuntu, tuning Linux kernel Proficiency with Ansible, Nvidia and CUDA toolkits, Kubernetes, and container orchestration Understanding of automation, monitoring, and security with GPU as a service Preferred experience Experience supporting HPE PCAI or other AI/HPC infrastructure and More ❯
Inference experience for high-throughput model serving - Proven ability to work on air-gapped systems with no external package repositories - Experience with GPU orchestration (NVIDIA A100/H100) and CUDA optimisation - Python expertise with offline dependency management and local package mirrors Technical Stack (All On-Premises) Models: Llama 3, Mistral, Qwen (locally hosted) Vector Stores: Chroma, FAISS, Milvus Orchestration More ❯