Platform Engineer (Full-time)

Strong Compute • San Francisco, CA

306d

About The Position

We’re building the operating system for AI compute—seamless workstation style access as a single entry point into global compute, with ultra fast data transit connecting everything. If you love high-performance computing, distributed systems, and AI infrastructure, and have experience managing large-scale GPU clusters and storage systems, you’ll fit right in.

Requirements

• Strong systems engineering skills with experience in distributed computing and storage for AI workloads
• Proficiency in GPU cluster management, including NVIDIA GPUs, Slurm, and Kubernetes
• Deep understanding of distributed training frameworks and multi-cloud architectures (AWS, GCP, Azure, and emerging GPU clouds)
• Experience managing large-scale clusters, including team leadership, hiring, and scaling operations
• Expertise in high-performance storage (Ceph, S3, ZFS, Lustre, and others) for massive AI datasets
• Ability to optimize cluster utilization, uptime, and scheduling for cost-effective operations
• Understanding of colocation strategies, managing AI data centers, and running HPC workloads in mixed environments
• DevOps/MLOps experience, automating training pipelines for large-scale AI models
• Experience working with AI/ML researchers, optimizing infrastructure for deep learning training

Responsibilities

• Scalable, distributed AI infrastructure across cloud, on-prem, and colocation environments
• GPU orchestration and fault-tolerant scheduling (Slurm, Kubernetes, Ray, and other orchestration frameworks)
• Supercomputing clusters and high-performance storage solutions for AI workloads
• Ultra-fast data pipelines for petabyte-scale AI training workloads
• Multi-cloud orchestration and on-premise AI data centers, making compute feel like a single, unified system
• DevOps & MLOps automation for streamlined model training and deployment
• Security and reliability for distributed computing across the public internet
• Scaling compute clusters 10-20x, from 128 to 1024+ GPUs, ensuring high uptime, reliability, and utilization
• Optimizing HPC clusters for AI training, including upgrade pathways and cost-efficiency strategies

Benefits

• Top spec Macbook + separate GPU cluster dev environments for each engineer
• Weekly cash bonus when you workout out 3+ times a week
• Comprehensive health benefits, including a choice of Kaiser, Aetna OAMC, and HDHP (HSA-eligible) plans for our SF-based team members
• Highest in the world 20 year exercise window for options

What This Job Offers

• Career Level: Senior