Platform Engineer
Overview:
In this role you will replace and run a gateway that unifies internal AI model requests, with built-in identity, budgets, routing, and audit. You'll own the platform end-to-end, supporting internal teams and enabling governed AI use cases. The position sits in Corporate IT Operations, collaborating with Security, Compliance, and Legal to ensure reliability, cost control, and secure access. This is a hands-on, platform-focused engineering role with a strong impact on how NetDocuments scales AI for the business. Compensation / Benefits 90% healthcare premiums coveredHSA contributions 401K match at 4% with immediate vesting Flexible PTO10 paid holidays Wellness and life activities contributions
Responsibilities:
- Deploy, configure, and operate the internal AI gateway for LLM traffic, including provider connections
- Integrate gateway with Microsoft Entra ID for SSO and RBAC; manage API keys with scoping, rotation, and revocation
- Own gateway availability, latency, capacity, upgrades, and change management
- Implement request path controls (redaction, DLP, audit logging) to meet Security, Compliance, and FedRAMPImplement and tune routing policy to direct requests to appropriate models by default; build spend attribution
- Configure budgets, rate limits, and hard stops; reduce avoidable consumption
- Handle intake and provisioning from AI use case request to governed access; coordinate with Security/Compliance/Legal
- Maintain incident response readiness, runbooks, and post-incident improvements
- Provide weekly platform updates on spend, adoption, health, incidents, and risks; support dashboards with data
- Document gateway configuration, provider connections, routing policy, and procedures
- Other duties as assigned
Key requirements:
- 4-5 years operating a cloud production service with on-call ownership
- Hands-on experience with API Gateways/Reverse Proxies & Service Mesh (Envoy, Kong, LiteLLM, Portkey, NGINX)OIDC/OAuth 2.0/SAML, RBAC design, credential lifecycle management
- Python or Go at middleware level; infrastructure as code; containerized deployment
- Observability/Instrumentation: metrics, logs, distributed tracing; telemetry mindset
- Usage-based cost attribution and chargeback; forecastable and enforceable spend
- Process design, technical documentation, and stakeholder reporting
- Bachelor's degree in Computer Science, Engineering, or related field (or equivalent)
- Cross-functional collaboration with Security, Compliance, LegalClear technical documentation for non-engineers
- Proactive problem solving and incident responseAWS or AzureAPI Gateway, Reverse Proxy & Service Mesh tooling (Envoy, Kong, LiteLLM, Portkey, NGINX)
- Authentication & Authorization via OIDC, OAuth 2.0, SAML, RBAC