Turing
Platform Engineer - Enterprise AI
New York, New York, United States · Full-time · Posted Oct 26, 2026
- Experience
- 6+ years; specifically, six or more years of platform or infrastructure engineering supporting production SaaS.
About the job
Build and operate Turing’s Enterprise AI platform, enabling reliable deployments across customer-controlled cloud accounts, dedicated instances, and sovereign environments.
What you'll do
- Develop platform services and model gateway, and build deployment systems for customer environments.
- Own CI/CD, infrastructure as code, deployment tooling, and secure multi-tenant reliability.
- Establish observability and cost telemetry; participate in on-call operations and incident response.
What they ask for
- 6+ years of platform or infrastructure engineering experience supporting production SaaS.
- Experience shipping products customers run in their own environments, such as VPC, self-hosted, or air-gapped environments.
- Deep expertise in at least one backend language and experience with cloud infrastructure, Kubernetes, and deployment tooling.
- Experience with on-call operations, incident response, and reliability/observability; familiarity with Postgres, object storage, queues, and vector stores.
Nice to have
- Model serving or model gateway experience, including vLLM, LiteLLM, or Triton; SOC 2 controls in CI.
- Experience operating AI systems in regulated or highly controlled environments.
Tools
Go, Ruby, Python, TypeScript, Kubernetes, Helm, Terraform, Pulumi
AI focus
Build the platform and model gateway for deploying AI systems across enterprise environments.
Model-written summary · the original posting is authoritative