WebAI
Staff Platform Engineer
Austin, TX · Staff · Full-time · Posted Oct 21, 2026
- Experience
- 8+ years building and operating production infrastructure; at least some experience on bare metal or on-prem, not only managed cloud.
About the job
Owns the architecture, implementation, security, deployment, and operations of webAI’s private-AI platform across customer hardware and cloud environments.
What you'll do
- Package, deploy, secure, observe, and upgrade the webAI kernel, B2B SDK, and local inference across bare metal and cloud.
- Build and operate inference serving, software supply chain, security, observability, reliability, and incident-response capabilities.
- Create deployment documentation and tooling, lead architecture evolution, and mentor engineers.
What they ask for
- 8+ years building and operating production infrastructure, including some bare-metal or on-prem experience.
- Deep experience with at least one workload orchestrator (Nomad or Kubernetes).
- Strong Terraform and configuration management (Ansible or similar); production experience with AWS, Azure, or both.
- Proficiency in at least one systems language (Rust or Go), plus scripting (Python/Bash).
Nice to have
- macOS fleet administration at scale.
- Experience running local LLM inference, including GPU/unified-memory capacity planning and model packaging.
Tools
Nomad, Kubernetes, Terraform, Ansible, AWS, Azure, GitLab, Prometheus
AI focus
Build the local model inference serving layer, including an OpenAI-compatible gateway, model and persona routing, and performance/load testing; support local LLM inference on customer hardware.
Model-written summary · the original posting is authoritative