Platform Engineer - Enterprise AI
Core
Build and operate the core services, model gateway, and multi-tenant infrastructure for Turing's Enterprise AI platform to enable reliable deployment in client environments.
Role type
Senior Platform Engineer (Enterprise AI Infrastructure)
Builds
Platform services, model gateway, multi-tenant infrastructure, CI/CD pipelines, and observability systems for enterprise AI deployments.
Domain
Enterprise AI, Cloud Infrastructure, SaaS
Deliverable
production ML models
Required skills
Backend development (Go, Ruby, Python, TypeScript), Kubernetes, Terraform/Pulumi, GitOps, Observability (OpenTelemetry, Prometheus, Datadog), Multi-tenant architecture, VPC/Self-hosted deployment, SOC 2 implementation
Preferred skills
Model serving (vLLM, LiteLLM, Triton), Regulated environment deployment, AI system operations
Technologies
Kubernetes, Helm, Terraform, Pulumi, GitOps, OpenTelemetry, Prometheus, Datadog, Postgres, vLLM, LiteLLM, Triton
Responsibilities
Design and build platform services and the model gateway; Create reliable deployment systems for client cloud accounts and sovereign environments; Maintain CI/CD and infrastructure as code; Operate production systems with on-call incident response; Build observability and FinOps telemetry.
Seniority
Senior, hands-on IC
