Principal Systems Engineer, RELIC Compute Architecture

Mountain View, California, United States of America

Full Time

5 hours ago

$260,000 - $300,000 USD

H1B Sponsor Likely

Key skills

AI/HPC Systems ArchitectureGPU ArchitectureNVLink and NVSwitchInfiniBandRoCEv2 PFCRoCEv2 ECNRoCEv2 DCQCNUALink and Ultra EthernetCPU and Host Architecture ArmCPU and Host Architecture x86CPU and Host Architecture NUMACPU and Host Architecture PCIeCPU and Host Architecture CXLInference Serving disaggregated servingInference Serving continuous batchingInference Serving paged attentionInference Serving KV-cacheInference Serving MoE parallelismInference Serving Frameworks SGLangInference Serving Frameworks vLLMInference Serving Frameworks TensorRT-LLMInference Serving Frameworks NVIDIA DynamoPerformance and TCO ModelingRack-Scale SystemsCollective Communication NCCLCollective Communication RCCLCollective Communication NVSHMEMLLM

About this role

Rune is hiring a Principal Systems Engineer to own the compute architecture for its next-generation RELIC platform. The role sets hardware and network direction, co-designs the inference stack, builds performance and cost models, and leads platform bring-up and validation.

Responsibilities:

Define the next-gen RELIC compute platform. Evaluate and select accelerators, host CPUs, NICs and DPUs across NVIDIA (Blackwell Ultra, Rubin), AMD (MI3xx/MI4xx) and emerging inference silicon. Make the call on HGX-class nodes versus rack-scale NVL systems for each site
Architect the scale-up domain. Size NVLink/NVSwitch domains and partitioning (e.g. NVL72-class racks), and track open alternatives such as UALink and Ethernet-based scale-up. Decide what domain size each workload actually needs
Architect the scale-out and front-end fabrics. Own topology (rail-optimized, fat-tree, multi-plane), RoCEv2 congestion control, Ultra Ethernet readiness, optics and transceiver strategy, and storage and KV-cache networks
Co-design the inference stack with the hardware. Map disaggregated prefill/decode, KV-cache transfer and offload, MoE expert parallelism, tensor/pipeline parallelism and speculative decoding onto the platform. Work hands-on with SGLang, vLLM, TensorRT-LLM and NVIDIA Dynamo
Build the models that drive decisions. Own performance, roofline and TCO models covering throughput, latency SLOs, perf/W, $/token and tokens/s/MW, and keep them honest against measured data from our clusters
Own the roadmap and vendor technical relationships. Lead deep-dives with NVIDIA, AMD, OEMs and network vendors; influence early-access programs; write the architecture specs that procurement and site teams build to
Stay close to the metal. Lead bring-up and validation of new platforms and drive root cause on fabric, NIC and node-level issues when they block production