Senior Hardware Engineer - GPU & AI Infrastructure
Core
Technical lead for GPU and AI accelerator ecosystem, ensuring optimized hardware for Roblox's massive-scale rendering and ML workloads.
Role type
Senior Hardware Engineer (GPU & AI Infrastructure)
Builds
High-density compute nodes, GPU-accelerated hardware platforms, and fleet integration for real-time rendering and low-latency AI inference.
Domain
Data Center Hardware / AI Infrastructure / High-Performance Computing
Deliverable
production ML models | infrastructure
Required skills
GPU architecture expertise, high-speed interconnects (NVLink/PCIe Gen5/6), firmware qualification (BIOS/BMC), Linux subsystem testing, Python/Go/C++ scripting, systemic debugging
Preferred skills
NVIDIA HGX/MGX platform experience, liquid cooling systems knowledge, HBM/DDR5/NVMe validation
Technologies
NVLink, PCIe Gen5/6, InfiniBand, Grafana, Prometheus, Linux, NVIDIA HGX/MGX
Responsibilities
Prototype next-generation GPU-accelerated hardware platforms; drive GPU integration, performance testing, and driver tuning; develop stress-testing strategies for GPU-heavy server platforms; lead firmware qualification and automation; provide technical guidance to hardware vendors; build monitoring stacks for GPU metrics.
Seniority
Senior, hands-on IC