Staff Platform Engineer
Posted Updated
Description
- WebAI runs private AI on the customer’s own hardware: on-prem Apple-silicon fleets (some air-gapped), Linux servers, and the customer’s own cloud
- As Staff Platform/Infrastructure Engineer you’ll own the substrate that makes this repeatable
- That means how our kernel, services and local model inference get packaged, deployed, secured, observed and upgraded across bare metal and cloud
- You’ll inherit a production deployment serving a global enterprise customer, lead its move to a leaner next-generation architecture, and turn it into a deployment kit our forward-deployed engineers can use to install a new customer from the docs alone
- This is a hands-on staff role: you’ll make the architecture calls, write the code and carry the pager
- Own deployment for the webAI kernel and B2B SDK. Deliver single-machine installs, multi-node clusters, and cloud (AWS, Azure/AKS) installs from one model, keeping the gap between cloud and bare metal small
- Choose and evolve our orchestration approach (Nomad, Kubernetes, or config-managed native services such as Ansible plus launchd) with simplicity as the goal. Cut custom infrastructure code where you can
- Run Apple-silicon fleets in production: launchd services, firewalling (pf), Lima/Docker VMs, GPU/unified-memory sizing for local LLM inference, and recovery after power loss or hardware failure
- Build the inference serving layer with the AI team: an OpenAI-compatible model gateway, conversation-pinned load balancing, routing per model and per persona, and performance/load testing (throughput, time to first token, concurrency)
- Own the software supply chain: GitLab CI, container and OCI model artifacts, signing (cosign/minisign), pinned dependencies, mirrored registries for air-gapped sites, and the release process
- Secure the platform: secrets management (Vault, KMS, cloud secret stores), PKI and mTLS, enterprise identity integration (Entra ID/OIDC, SCIM), and network policy for on-prem sites
- Build observability and audit: metrics, logs and alerting (Prometheus, Loki, Grafana), plus export of audit and telemetry into customer monitoring tools
- Define what high availability means for us. Set reliability levels and SLOs we can commit to in customer contracts, then build them
- Write the runbooks, “recipes” and RCAs that let forward-deployed engineers and customers operate the stack without you. Lead incident response when they can’t
- Work with kernel engineers on networking (QUIC/peer-to-peer connectivity, relays, NAT traversal) and on making the kernel easy to deploy
- Mentor engineers and raise the bar for infrastructure-as-code, testing and operations across the team
Benefits
- Grow with us: Equity options so you share in our growth. Build your future as we build ours.
- Family first: Parental leave and fertility support for every stage of life. Your family matters here.
- Plan your future: A 401(k) to help you save and invest. Secure what’s ahead with confidence.
- Stay well: Comprehensive health coverage for body and mind. Because balance fuels great work.
- Keep learning: A stipend to explore, study, and sharpen your skills. Growth never stops.
- Work anywhere: Remote-first with flexible time off to recharge. Find balance wherever you are.
- Running local LLM inference (llama.cpp, MLX, vLLM), GPU/unified-memory capacity planning, model packaging
- Proficiency in at least one systems language (Rust or Go), plus scripting (Python/Bash)
- MacOS fleet administration at scale (launchd, pf, MDM-managed or locked-down environments, FileVault constraints)
- Clear technical writing: runbooks, design docs and RCAs that others can act on
- Production experience with AWS, Azure, or both (identity/IAM, KMS, container registries, managed Kubernetes)
- Observability: Prometheus/Grafana/Loki or equivalent, alert design, running on-call
- CI/CD and release engineering in GitLab: container builds, artifact signing, reproducible pinned builds
- Strong Terraform and configuration management (Ansible or similar). Clean state and environment management across staging and production
- 8+ years building and operating production infrastructure. At least some of it on bare metal or on-prem, not only managed cloud
- Deep experience with at least one workload orchestrator (Nomad or Kubernetes), and the judgment to know when not to use one
- Solid networking fundamentals: WireGuard/Tailscale or other VPN overlays, firewalls, NAT, load balancers and L4/L7 proxies (e.g. Envoy), DNS and TLS
- Secrets and identity: Vault or equivalent, PKI/mTLS, OIDC
- Air-gapped or disconnected delivery: mirrored registries, offline installers
- Peer-to-peer or QUIC networking (e.g. iroh, libp2p), relays and NAT traversal
- Writing Kubernetes operators/controllers or Nomad tooling (kube-rs, controller-runtime)
- Customer-facing deployment experience: installing and supporting software at customer sites
Skills
Sign in to read and join the discussion.