Staff Platform / Infrastructure Engineer
webAI is an Austin-based sovereign AI company developing local-first, specialized AI systems that organizations can build, deploy, and operate on infrastructure they own.
Projects
About webAI
webAI provides collaborative intelligence software centered on the webAI App, specialized Personas, and its Intelligence Delivery Network. Its platform is designed to keep intelligence close to organizational data and hardware, support private and specialized models, and enable teams to build, share, and improve AI without relying exclusively on centralized cloud systems.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will own the platform infrastructure supporting private AI deployments on customer hardware and cloud environments. You will design and implement deployment, orchestration, inference serving, software supply-chain security, observability, reliability, and incident-response capabilities. You will write operational documentation, collaborate on networking and kernel deployment, and mentor engineers on infrastructure, testing, and operations.
Requirements
- 8+ years building and operating production infrastructure, including bare-metal or on-premises infrastructure
- Experience with Nomad or Kubernetes
- Terraform and configuration management experience
- Production experience with AWS, Azure, or both
- Networking knowledge including VPN overlays, firewalls, NAT, load balancers, proxies, DNS, and TLS
- Experience with secrets management, PKI, mTLS, and OIDC
- GitLab CI/CD and release-engineering experience
- Observability and on-call experience
- Proficiency in Rust or Go and Python or Bash scripting
- Technical writing experience for runbooks, design documents, and RCAs
Responsibilities
- Own deployment for the webAI kernel and B2B SDK across single-machine, multi-node, and AWS or Azure installations
- Choose and evolve the workload orchestration approach
- Operate Apple-silicon fleets, including services, firewalling, virtual machines, inference sizing, and failure recovery
- Build the model inference serving layer, including gateway, load balancing, routing, and performance testing
- Own the software supply chain, including GitLab CI, artifacts, signing, dependency pinning, registries, and releases
- Secure the platform with secrets management, PKI, mTLS, identity integration, and network policy
- Build observability, alerting, audit exports, reliability levels, and SLOs
- Write runbooks, deployment recipes, and RCAs, and lead incident response
- Work on networking and deployability with kernel engineers
- Mentor engineers and improve infrastructure-as-code, testing, and operations
Benefits
- Health, dental, and vision insurance
- High-deductible HSA option with company contribution
- 401k match for US-based employees
- Flexible PTO
- Parental leave for eligible employees
- Continuing education support
- Company-paid basic life insurance
- Supplemental life insurance
- Company-paid short- and long-term disability insurance
- Free parking for in-office employees
