Staff Platform / Infrastructure Engineer
Core
Design and operate the substrate for private, distributed AI inference on customer hardware (bare metal, Apple Silicon, cloud), ensuring secure deployment and scalability.
Role type
Staff Platform/Infrastructure Engineer
Builds
Production deployment kits for webAI kernel and B2B SDK across bare metal and cloud environments.
Domain
AI Infrastructure / Distributed Systems / Cloud & On-Prem
Deliverable
production ML models
Required skills
Kubernetes or Nomad, Terraform, AWS/Azure, Rust or Go, Networking (WireGuard, NAT, Load Balancing), Secrets Management (Vault), CI/CD (GitLab), Observability (Prometheus/Grafana/Loki)
Preferred skills
macOS fleet administration, Local LLM inference (llama.cpp, MLX), Air-gapped delivery, Kubernetes operators
Technologies
Nomad, Kubernetes, Terraform, Ansible, AWS, Azure, AKS, GitLab, Vault, Prometheus, Grafana, Loki, Rust, Go, Python, Bash, WireGuard, Envoy, mTLS, OIDC, SCIM
Responsibilities
Own deployment for the webAI kernel and B2B SDK; Choose and evolve orchestration approach; Run Apple-silicon fleets in production; Build the inference serving layer; Own the software supply chain; Secure the platform; Build observability and audit; Define high availability and SLOs; Write runbooks and lead incident response; Work with kernel engineers on networking; Mentor engineers.
Seniority
Staff, hands-on IC with architecture and mentorship responsibilities
