RDMA Performance Engineer
Job Summary
To support a project team focused on SONiC validation for AI Networking, the fully remote RDMA Performance Engineer will configure, troubleshoot, and maintain NVIDIA/Mellanox Spectrum switches and ConnectX Network Interface Cards (NICs), while optimizing network environments for maximum performance.
Key responsibilities
- Implement and tune advanced congestion control mechanisms for AI workloads, including RoCEv2 and PFC
- Conduct performance benchmarking and validation testing on AI-ready data center fabrics utilizing RDMA and the NVIDIA Collective Communication Library (NCCL)
- Author and maintain technical documentation detailing network designs, configurations, and benchmarking results
Required qualifications
- 7+ years of professional experience in network engineering, with 3+ years focused on data center network design and architecture
- Hands-on experience with core network protocols and technologies, including BGP, EVPN/VXLAN, and LACP
- Proven experience configuring and troubleshooting NVIDIA/Mellanox Spectrum switches and ConnectX NICs
- Deep understanding of AI-dedicated data center designs and congestion control mechanisms
- Experience conducting performance benchmarking for AI-ready data center fabrics utilizing RDMA
Complete Job Description
The complete job description is available to members. Premium membership includes:
Full access to 41,336 remote jobs from human-vetted companies, updated daily
Resume Builder - AI-powered tool to craft, enhance, and tailor your resume to a specific job
Twice-monthly live group coaching and the full Remote Career Center
20% member discount on Career Services
Backed by a 30-day money-back guarantee
Company Company Name
Headquarters Headquarters
Founded Founded
Website
The company description is available to members. Go Premium for full access to every job and company profile in our remote jobs database, backed by a 30-day money-back guarantee.
