SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Volta is building a vertically integrated AI infrastructure platform with a mission to make compute as reliable and available as electricity. The company has secured $10B in strategic partnerships and Series A funding from Andreessen Horowitz, operating across London, Palo Alto, and New York with rapid growth plans.
This Senior Network Engineer role is part of a platform engineering team responsible for designing, building, and operating large-scale GPU compute infrastructure networks. The network is a core component of Volta's platform, not a supporting layer. You will work on fabric design, overlay and multi-tenancy, edge connectivity, and the software that programs and observes the entire system.
Key responsibilities include:
- Design and operate network fabric across sites: leaf-spine Ethernet, BGP underlay, EVPN/VXLAN overlay, and multi-tenant isolation
- Build software that manages the fabric: configuration generation, validation pipelines, drift detection, and safe change tooling
- Contribute production Python or Go code to the platform, integrating physical fabric with IaaS control plane
- Define network APIs and abstractions for tenant isolation and performance
- Instrument the fabric with streaming telemetry and topology-aware metrics
- Debug complex problems: congestion, packet loss under collective communication load, and controller/hardware state disagreements
- Participate in on-call, incident response, and structural problem resolution
- Evaluate OEM and partner designs against requirements
- Collaborate in code review and technical design discussions
Depending on background, you may specialize in GPU fabric (RoCE v2, InfiniBand, congestion control), SDN/overlay integration, edge connectivity (BGP peering, transit relationships), or fabric observability.
Required qualifications: 4+ years in data center or cloud network engineering with production experience; deep Ethernet fabric knowledge (leaf-spine, BGP, ECMP); EVPN/VXLAN in production; production software development in Python or Go with proper testing and CI; network automation experience (configuration as code, NetBox/Nautobot); solid Linux fundamentals; Kubernetes networking familiarity; multi-vendor capability; willingness to be on-site during cluster bring-up; strong written communication skills.
Nice-to-have skills include AI-assisted development tools, RoCE v2 at scale, InfiniBand production experience, NVIDIA Spectrum-X, gNMI/OpenConfig/NETCONF, IPv6 at production scale, and ASN operations.
