Staff Platform/Infrastructure Engineer (AI)

Location: Austin, Texas, United States

Company

hirify.global is building distributed AI infrastructure for private, personalized AI running on customer-owned hardware and cloud environments.

What you will do

• Own deployment of the hirify.global kernel and B2B SDK across single machines, multi-node clusters, AWS, and Azure/AKS.
• Choose and evolve orchestration using Nomad, Kubernetes, Ansible, launchd, or comparable approaches, while reducing custom infrastructure code.
• Operate Apple-silicon production fleets and support local LLM inference, including service management, firewalling, virtualization, capacity planning, and hardware recovery.
• Build the inference serving layer, including an OpenAI-compatible gateway, conversation-pinned load balancing, model and persona routing, and performance testing.
• Own software supply chain security, secrets, identity, PKI/mTLS, network policy, observability, audit exports, release engineering, and air-gapped delivery.
• Define availability targets and SLOs, write runbooks and RCAs, lead incident response, collaborate on QUIC and peer-to-peer networking, and mentor engineers.

Requirements

• 8+ years building and operating production infrastructure, including experience with bare metal or on-premises environments.
• Deep experience with Nomad or Kubernetes and the judgment to determine when orchestration is unnecessary.
• Strong Terraform and configuration-management experience with Ansible or similar tools, including staging and production state and environment management.
• Production experience with AWS, Azure, or both, including identity/IAM, KMS, container registries, and managed Kubernetes.
• Solid networking fundamentals covering WireGuard/Tailscale or other VPN overlays, firewalls, NAT, load balancers, L4/L7 proxies such as Envoy, DNS, and TLS.
• Experience with Vault or an equivalent secrets system, PKI/mTLS, and OIDC.
• GitLab CI/CD and release-engineering experience with container builds, artifact signing, and reproducible pinned builds.
• Observability experience with Prometheus, Grafana, Loki, or equivalent tools, including alert design and on-call operations.
• Proficiency in Rust or Go plus scripting in Python or Bash, and clear technical writing for runbooks, design documents, and RCAs.

Nice to have

• Large-scale macOS fleet administration, including launchd, pf, MDM-managed or locked-down environments, and FileVault constraints.
• Local LLM inference with llama.cpp, MLX, or vLLM, GPU/unified-memory capacity planning, and model packaging.
• Air-gapped or disconnected delivery with mirrored registries and offline installers.
• Peer-to-peer or QUIC networking, relays, and NAT traversal.
• Kubernetes operator/controller or Nomad tooling development.
• Customer-facing deployment and support experience at customer sites.

Culture & Benefits

• Values include truth, ownership, tenacity, and humility.
• Competitive salary and performance-based incentives.
• Health, dental, vision, and high-deductible HSA benefits with company contribution.
• 401(k) match for U.S.-based employees, flexible PTO, parental leave, and continuing education support.
• Company-paid life insurance and short- and long-term disability coverage; free parking for in-office employees.
• Benefits for employees outside the United States vary according to local law, country requirements, and the employing platform or entity.