- Home
- ...
- Open Positions
- Job detail
Description
Description
We are seeking a hands-on engineer to build, deploy, and maintain high-performance compute and storage infrastructure for AI workloads. The role spans the full stack from physical server and VM's bring-up, Linux operating system deployment and patching, network configuration, through high-performance networking technologies such as DPDK and RDMA, to the deployment and optimization of AI/LLM serving environments including vLLM, LMCache, etc. and performance tuning / benchmarking.
Responsibilities:
- Rack, install, and commission physical servers and networking equipment in lab and production environments.
- Install, configure, and troubleshoot Linux-based operating systems and infrastructure services.
- Configure and validate network connectivity, including Ethernet fabrics, high-speed interconnects, routing, VLANs, and network security settings.
- Deploy, tune, and troubleshoot high-performance networking technologies, including, but not limited to:
- DPDK
- RDMA / RoCE
- SR-IOV
- Perform server validation, benchmarking, performance characterization, and system health monitoring.
- Bring up and maintain distributed application environments and AI infrastructure stacks.
- Deploy, configure, and optimize LLM serving platforms such as:
- vLLM
- LMCache
- Model serving frameworks
- GPU software stack and drivers
- Collaborate with hardware, software, networking, and AI engineering teams to optimize end-to-end system performance.
- Develop automation scripts and deployment tools for infrastructure provisioning and validation.
- Debug complex issues spanning hardware, operating systems, networking, storage, and application layers.
- Document deployment procedures, best practices, and operational runbooks.
Mandatory:
- Experience bringing up and configuring physical servers and data center infrastructure.
- Strong hands-on experience with Linux system administration and troubleshooting, including Linux kernel patching and configuration
- Solid understanding of networking fundamentals and high-speed network technologies.
- Experience with DPDK, RDMA/RoCE, SR-IOV, or similar performance-oriented networking technologies.
- Familiarity with server hardware, BIOS/UEFI/Firmware configuration, NICs, storage devices, and system validation.
- Experience deploying and operating distributed applications in Linux environments.
- Proficiency in scripting and automation using Python, Bash, or similar languages.
- Strong analytical and troubleshooting skills across multiple technology domains.
Preferred:
- Experience with GPU/DPU-based systems and AI infrastructure.
- Familiarity with vLLM, LMCache or alike
- Familiarity with Kubernetes, Docker, or other containerized deployment environments.
- Experience with performance analysis and benchmarking tools.
- Knowledge of storage technologies, NVMe, high-performance filesystems, and distributed storage systems.
- Background in AI/ML infrastructure, model serving, or large-scale distributed systems.
- Familiarity with the SW aspects of SoC bring-up
Ideal Candidate:
The ideal candidate is a hands-on, systems-oriented engineer who enjoys taking a system from bare metal to a fully operational high-performance AI platform.
He is comfortable working across hardware, Linux, virtualization, networking and application layers
and thrives on solving complex integration and performance challenges.