Fal Ai
Senior/Staff Software Engineer, Network Infrastructure
Remote - USA. Posted 3 months ago
The role
You will build the public and private network infrastructure connecting all of fal's data centers and cloud environments. This includes supporting the public serverless platform and custom compute clusters through internet routing, private connectivity, and high-performance Linux networking.
What you will do
- Design, build, validate, and operate public and private networks
- Use AI to automate network provisioning, configuration, validation, monitoring, and recovery
- Manage ASNs, public IP prefixes, and private address space
- Build and operate BGP routing including route policies, communities, filtering, traffic engineering, and failover
- Announce customer and company IP ranges from physical infrastructure and cloud providers
- Establish private peering with customers, partners, data centers, internet exchanges, and cloud providers
- Build private and overlay networks using VXLAN, IPsec, WireGuard, and Tailscale
- Operate DNS networking patterns including anycast DNS and mDNS
- Tune the Linux networking stack for high throughput, low latency, and large connection counts
- Build network observability and diagnostics using metrics, logs, flow data, active probes, and packet captures
Required qualifications
- 5+ years building and operating production network infrastructure
- Strong Linux networking: routing tables, policy routing, network namespaces, bonding, VLANs, bridges, firewalling, NAT, conntrack
- Deep BGP knowledge: route selection, communities, filtering, convergence, multipath, troubleshooting
- Experience managing ASNs, public IP space, BGP announcements, IPAM, RPKI/ROAs, IRR records
- Experience designing private IPv4/IPv6 address plans and preventing cross-customer/region conflicts
- Production VXLAN overlay network experience
- Production IPsec, WireGuard, or Tailscale experience
- Experience with anycast DNS and mDNS
- Experience with private peering and cloud provider interconnects
- Linux networking performance tuning: congestion control, queue disciplines, socket buffers, MTU, NIC offloads, RSS/RPS/XPS, IRQ affinity
- Packet-level troubleshooting: iproute2, tc, ethtool, tcpdump, Wireshark, mtr
- Ansible or equivalent network configuration automation
Nice to have
- EVPN as a VXLAN control plane
- FRRouting, BIRD, or similar software-routing platforms
- AWS Direct Connect, Google Cloud Interconnect, Azure ExpressRoute
- Internet exchanges, cross-connects, route servers, colocation networking
- DDoS detection, mitigation, scrubbing, BGP-based traffic diversion
- eBPF, XDP, DPDK
- NetBox, Nautobot, Nornir
- Authoritative or recursive DNS infrastructure at scale
- Network hardware: Arista, Juniper, Cisco
- Kubernetes networking, service load balancing, CNI
Benefits
- Interesting and challenging work
- A lot of learning and growth opportunities
- Visa sponsorship
- Relocation help to San Francisco
- Health, dental, and vision insurance (US)
- Regular team events and offsites
Before you apply
- We offer visa sponsorship
About the company
fal is the generative media ecosystem powering the next generation of AI products. They build infrastructure, tools, and model access for developers and enterprises.