10 hours ago
Responsibilities
- Own deployment of the webAI kernel and B2B SDK across single-machine, multi-node, bare-metal, on-premises, and cloud installations.
- Choose and evolve the orchestration approach using Nomad, Kubernetes, Ansible, launchd, or other appropriate tooling.
- Operate Apple-silicon production fleets, including launchd services, firewalling, virtual machines, GPU and unified-memory sizing, and hardware recovery.
- Build an OpenAI-compatible inference gateway with conversation-pinned load balancing, model and persona routing, and performance testing.
- Own the software supply chain, including GitLab CI, container and OCI model artifacts, signing, pinned dependencies, mirrored registries, and releases.
- Secure the platform through secrets management, PKI, mTLS, enterprise identity integration, and on-premises network policy.
- Build metrics, logs, alerting, audit exports, and telemetry integrations for customer monitoring tools.
- Define availability targets, reliability levels, and SLOs, and implement the systems required to meet them.
- Write runbooks, deployment recipes, and root-cause analyses; lead incident response and pager coverage.
- Collaborate on QUIC, peer-to-peer connectivity, relays, NAT traversal, and kernel deployability.
- Mentor engineers and improve infrastructure-as-code, testing, and operational practices.
Requirements
- At least 8 years of experience building and operating production infrastructure, including some bare-metal or on-premises experience.
- 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.
- Production experience with AWS, Azure, or both, including identity/IAM, KMS, container registries, or managed Kubernetes.
- Strong networking fundamentals covering VPN overlays, firewalls, NAT, load balancers, L4/L7 proxies, DNS, and TLS.
- Experience with Vault or an equivalent secrets system, PKI/mTLS, and OIDC.
- Experience with GitLab CI/CD, container builds, artifact signing, and reproducible pinned builds.
- Experience with Prometheus, Grafana, Loki, or equivalent observability systems, including alerting and on-call operations.
- Proficiency in Rust or Go plus scripting with Python or Bash.
- Ability to write actionable runbooks, design documents, and root-cause analyses.
- Preferred experience includes macOS fleet administration, local LLM inference with llama.cpp, MLX, or vLLM, air-gapped delivery, QUIC or peer-to-peer networking, Kubernetes operators or Nomad tooling, and customer-facing deployment work.
Benefits
- Competitive salary and performance-based incentives.
- Health, dental, and vision benefits, including a high-deductible HSA option with company contribution.
- 401(k) match for U.S.-based employees.
- Flexible paid time off and parental leave for eligible employees.
- Continuing education support.
- Company-paid basic life insurance, supplemental life insurance, and short- and long-term disability coverage.
- Free parking for in-office employees.
- Benefits may vary for employees hired outside the United States based on local law, country-specific requirements, and the employment platform or entity.
Tech Stack
Categories
About webAI
webAI builds an end-to-end platform for training, deploying, and operating private AI models on infrastructure customers control, including edge devices. It sells enterprise software and developer SDKs/APIs used by public-sector, defense, aviation, and manufacturing teams to run specialized models with data sovereignty. Founded in 2020 and headquartered in Austin, Texas, the privately held company focuses on distributed AI/LLM infrastructure across local and cloud environments.