<p>We are looking for an experienced GPU DevOps / Infrastructure Setup Engineer to build, configure, deploy, and maintain GPU-enabled infrastructure for AI/ML and High-Performance Computing (HPC) workloads.</p><p>The ideal candidate will have hands-on experience with GPU server setup, on-premises AI infrastructure, Linux administration, NVIDIA GPU drivers, CUDA, containerization, infrastructure automation, and GPU workload deployment.</p><p>Experience with NVIDIA Base Command Manager (BCM), GPU cluster bring-up, InfiniBand networking, and LLM application deployment will be highly preferred. Candidates with experience across different GPU hardware vendors and cloud, on-premises, or hybrid environments are welcome.</p><p>Key Responsibilities</p><ul><li>Set up, configure, and maintain GPU-enabled servers, compute nodes, and AI infrastructure.</li><li>Build and deploy on-premises AI infrastructure and GPU compute clusters.</li><li>Perform end-to-end GPU cluster bring-up, including provisioning, configuration, validation, and testing.</li><li>Configure and manage NVIDIA Base Command Manager (BCM) for cluster deployment and management, where applicable.</li><li>Install and configure operating systems, GPU drivers, CUDA Toolkit, libraries, and supporting software.</li><li>Deploy and maintain GPU workloads on bare-metal servers, cloud platforms, and hybrid environments.</li><li>Configure GPU-enabled Docker containers and Kubernetes workloads.</li><li>Deploy and manage LLM applications using frameworks such as vLLM, Ollama, Hugging Face Text Generation Inference (TGI), or NVIDIA Triton.</li><li>Configure and troubleshoot GPU hardware, driver compatibility, CUDA initialization, memory utilization, and workload execution issues.</li><li>Support InfiniBand networking and high-speed interconnects for multi-GPU or multi-node environments.</li><li>Automate infrastructure provisioning, configuration management, and deployment using appropriate scripting and automation tools.</li><li>Develop and maintain CI/CD pipelines for infrastructure and application deployments.</li><li>Monitor GPU utilization, memory, temperature, power consumption, system health, and performance.</li><li>Implement monitoring, logging, alerting, health checks, and automated recovery using tools such as Prometheus and Grafana.</li><li>Optimize GPU utilization, VRAM consumption, inference latency, throughput, and overall infrastructure performance.</li><li>Troubleshoot Linux, networking, storage, container, hardware, and application deployment issues.</li><li>Perform infrastructure upgrades, patching, maintenance, capacity planning, and resource scaling.</li><li>Maintain technical documentation, installation procedures, configuration guides, and troubleshooting records.</li><li>Collaborate with AI/ML, development, platform, and infrastructure teams to support production workloads.</li></ul><p>Required Technical Skills</p><p><strong>GPU Infrastructure and Hardware</strong></p><ul><li>Hands-on experience with GPU server setup, configuration, and operations.</li><li>Knowledge of GPU hardware, server components, PCIe, power requirements, cooling, and hardware compatibility.</li><li>Experience with GPU models such as NVIDIA A100, H100, H200, L40S, RTX series, or equivalent GPU platforms.</li></ul><p><strong>Linux, Drivers, and CUDA</strong></p><ul><li>Strong Linux administration and troubleshooting skills.</li><li>Experience installing and configuring GPU drivers, CUDA Toolkit, and supporting libraries.</li><li>Ability to validate GPU detection, driver functionality, CUDA compatibility, and workload execution.</li></ul><p><strong>AI Infrastructure and HPC</strong></p><ul><li>Experience building or maintaining on-premises AI infrastructure.</li><li>Understanding of GPU cluster provisioning, compute nodes, and cluster validation.</li><li>Experience with NVIDIA Base Command Manager (BCM) is preferred.</li><li>Experience deploying on-premises GPU infrastructure without BCM is also valuable.</li><li>Knowledge of InfiniBand, RDMA, and high-speed networking for GPU clusters is an advantage.</li></ul><p><strong>DevOps and Containerization</strong></p><ul><li>Experience with Docker and GPU-enabled containers.</li><li>Kubernetes experience for GPU workload deployment and orchestration.</li><li>Infrastructure automation using Bash, Python, Ansible, Terraform, or equivalent tools.</li><li>Familiarity with CI/CD pipelines, Git, configuration management, and infrastructure monitoring.</li></ul><p><strong>LLM Deployment and Performance</strong></p><ul><li>Experience deploying LLM applications on GPU-enabled cloud instances or on-premises GPU servers.</li><li>Familiarity with vLLM, Ollama, Hugging Face TGI, NVIDIA Triton, or equivalent model-serving frameworks.</li><li>Understanding of API-based model serving and GPU resource allocation.</li><li>Experience troubleshooting GPU memory issues and optimizing inference performance.</li><li>Familiarity with Prometheus, Grafana, NVIDIA SMI, or DCGM for GPU monitoring.</li></ul><p>Experience Requirements</p><ul><li>3+ years of experience in DevOps, SRE, platform engineering, or infrastructure engineering.</li><li>At least 1–2 years of hands-on experience working with GPU environments.</li><li>Demonstrated experience in at least one real-world GPU infrastructure or AI deployment project.</li><li>Ability to explain the infrastructure architecture, GPU hardware used, individual responsibilities, deployment process, and technical issues resolved.</li><li>Experience supporting production environments is preferred.</li></ul><p>Preferred Qualifications</p><ul><li>End-to-end GPU cluster deployment using NVIDIA BCM.</li><li>Hands-on InfiniBand configuration and troubleshooting.</li><li>Bare-metal GPU server installation and configuration without Docker.</li><li>Multi-GPU or multi-node cluster deployment.</li><li>Production LLM serving and GPU performance optimization.</li><li>Experience across on-premises, cloud, and hybrid infrastructure environments.</li></ul><p>Candidate Profile</p><p>We are looking for engineers with practical infrastructure experience who can independently configure GPU environments, troubleshoot complex technical issues, and support reliable AI/ML and HPC deployments.</p><p>Candidates must be able to explain real projects they have worked on, the GPU hardware and tools used, their individual contributions, and the challenges they successfully resolved.</p>