Staff Platform / Infrastructure Engineer

webAI • Austin, TX

2d

About The Position

webAI is building distributed AI infrastructure for personalized AI, enabling enterprises to run large-scale AI models on consumer hardware while keeping their data and intellectual property private. The company is developing a secure, scalable, user-controlled end-to-end platform.

The Staff Platform / Infrastructure Engineer will own the deployment substrate for private AI running on customer-owned hardware and cloud environments, including on-premises Apple-silicon fleets, some of which are air-gapped, Linux servers, and customer clouds. The role covers packaging, deploying, securing, observing, and upgrading the webAI kernel, services, and local model inference across bare metal and cloud. The engineer will take responsibility for an existing production deployment serving a global enterprise customer, lead its migration to a leaner architecture, and create a deployment kit that forward-deployed engineers can use to install new customers from documentation. This is a hands-on staff role involving architecture decisions, coding, and on-call responsibilities.

Requirements

• At least 8 years of experience building and operating production infrastructure, including some bare-metal or on-premises experience.
• Deep experience with at least one workload orchestrator, such as Nomad or Kubernetes, and the judgment to know when not to use one.
• Strong Terraform and configuration-management skills, such as Ansible, including clean state and environment management across staging and production.
• Production experience with AWS, Azure, or both, including identity/IAM, KMS, container registries, and managed Kubernetes.
• Strong networking fundamentals, including VPN overlays such as WireGuard or Tailscale, firewalls, NAT, load balancers, L4/L7 proxies, DNS, and TLS.
• Experience with secrets and identity systems, including Vault or an equivalent, PKI/mTLS, and OIDC.
• CI/CD and release-engineering experience with GitLab, including container builds, artifact signing, and reproducible pinned builds.
• Experience with observability tools such as Prometheus, Grafana, and Loki or equivalents, alert design, and on-call operations.
• Proficiency in at least one systems language, Rust or Go, plus scripting in Python or Bash.
• Clear technical writing skills for runbooks, design documents, and actionable RCAs.

Nice To Haves

• Experience administering macOS fleets at scale, including launchd, pf, MDM-managed or locked-down environments, and FileVault constraints.
• Experience running local LLM inference with tools such as llama.cpp, MLX, or vLLM, including GPU/unified-memory capacity planning and model packaging.
• Experience with air-gapped or disconnected delivery, including mirrored registries and offline installers.
• Experience with peer-to-peer or QUIC networking, such as iroh or libp2p, relays, and NAT traversal.
• Experience writing Kubernetes operators/controllers or Nomad tooling, such as kube-rs or controller-runtime.
• Customer-facing deployment experience, including installing and supporting software at customer sites.

Responsibilities

• Own deployment of the webAI kernel and B2B SDK, delivering single-machine, multi-node cluster, and cloud installations through a consistent model.
• Choose and evolve an orchestration approach, favoring simplicity and reducing custom infrastructure code where practical.
• Operate Apple-silicon fleets in production, including launchd services, firewalling, Lima/Docker VMs, capacity sizing for local LLM inference, and recovery from power loss or hardware failure.
• Build the inference serving layer with the AI team, including an OpenAI-compatible model gateway, conversation-pinned load balancing, model- and persona-based routing, and performance and load testing.
• Own the software supply chain, including GitLab CI, container and OCI model artifacts, artifact signing, pinned dependencies, mirrored registries for air-gapped sites, and release processes.
• Secure the platform through secrets management, PKI and mTLS, enterprise identity integration, and network policies for on-premises sites.
• Build observability and auditing, including metrics, logs, alerting, and export of audit data and telemetry to customer monitoring tools.
• Define high availability, reliability levels, and customer-contract SLOs, and implement them.
• Write runbooks, deployment recipes, and RCAs so forward-deployed engineers and customers can operate the stack; lead incident response when needed.
• Collaborate with kernel engineers on networking, including QUIC and peer-to-peer connectivity, relays, NAT traversal, and kernel deployability.
• Mentor engineers and improve infrastructure-as-code, testing, and operational practices across the team.

Benefits

• Competitive salary and performance-based incentives.
• Comprehensive health, dental, and vision benefits package.
• High-deductible HSA option with company contribution.
• 401(k) match for U.S.-based employees.
• Flexible PTO policy.
• Parental leave for eligible employees.
• Continuing education support.
• Basic company-paid life insurance.
• Supplemental life insurance.
• Company-paid short- and long-term disability.
• Free parking for in-office employees.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed