HPC Architect

HPC ArchitectSan Francisco, CaliforniaAbout CamberCamber is on a mission to democratize scientific computing from astrophysics to genomics. Currently, distributed scientific workloads are nearly 100% on-premise, making computation for researchers limited in scope, with long iteration cycles. Our fully managed, infrastructure-free platform allows researchers to deploy on-demand fully managed instances for distributed scientific simulations and data analysis. We're based in San Francisco and backed by top venture capital firms Pear VC and Base 10 Partners.About The RoleCamber is seeking a visionary, highly motivated science and research computing expert. The HPC Architect is responsible for designing, implementing, and optimizing high-performance computing environments to support complex computational workloads, in our cloud platform. This role combines deep technical expertise with strategic foresight to develop scalable, efficient computing solutions.ResponsibilitiesDesign and architect high-performance computing infrastructure, including hardware, software, and network componentsEvaluate and select appropriate technologies to meet performance, scalability, and efficiency requirementsDevelop comprehensive HPC solutions that align with business objectives and research needsCollaborate with engineers and scientists to quickly iterate on the optimal solutionOptimize existing HPC environments for performance, energy efficiency, and cost-effectivenessCreate detailed documentation of system architecture, configurations, and best practicesStay current with emerging HPC technologies, frameworks, and methodologiesDevelop strategies for system monitoring, maintenance, and upgradingQualifications: Bachelor's degree in Computer Science, Engineering, or related field; advanced degree preferred5+ years of experience in HPC environments, with demonstrated expertise in architecture designStrong knowledge of parallel computing, distributed systems, and computational optimizationExperience with job scheduling systems (e.g., Slurm, PBS, LSF)Proficiency in HPC programming models (MPI, OpenMP, CUDA)Familiarity with various storage solutions (parallel file systems, object storage)Understanding of networking technologies relevant to HPC (InfiniBand, OmniPath, etc.)Knowledge of containerization and virtualization in HPC contextsExperience with system monitoring and performance analysis toolsExcellent problem-solving and analytical skillsBenefitsCompetitive salary and meaningful equityA flexible vacation policyComprehensive health, vision, dental, and life insurance as well as disability benefitsBeing part of and building out a world-class team

Created: 2025-06-19