Platform Engineer (Enterprise AI)

Location: New York City, Madison Square Park area, United States; hybrid work model with regular in-office presence.

Company

AI technology company building datasets, reinforcement learning environments, research benchmarks, and end-to-end agentic AI systems for frontier AI labs and enterprise customers.

What you will do

• Design, build, and operate core platform services, including platform infrastructure and the model gateway.
• Create reliable deployment systems for client cloud accounts, dedicated instances, and sovereign environments.
• Build and maintain CI/CD, infrastructure as code, and deployment tooling using Kubernetes, Helm, Terraform or Pulumi, and GitOps practices.
• Design secure multi-tenant systems with clear service ownership, operational accountability, and maintainability.
• Establish platform observability through service-level objectives, structured logging, metrics, tracing, and alerting.
• Develop telemetry to track model and compute costs by tenant, and participate in on-call operations and incident response.

Requirements

• Six or more years of platform or infrastructure engineering experience supporting production SaaS.
• Experience shipping products that customers run in their own environments, including VPC, self-hosted, or air-gapped environments.
• Deep expertise in at least one backend language such as Go, Ruby, Python, or TypeScript, with the ability to read and work across the others.
• Deep experience with at least one cloud and comfort working in a second, including private networking, KMS, IAM, Kubernetes, Helm, Terraform or Pulumi, and GitOps.
• Experience carrying a pager, running incidents, and owning reliability and observability.
• Familiarity with Postgres, object storage, queues, and vector stores.
• Production software engineering experience is required; candidates limited to cloud operations or ticket-queue DevOps without software engineering experience are not a fit.
• Experience operating multi-tenant systems is required.

Nice to have

• Experience with model serving and model gateways, including vLLM, LiteLLM, or Triton.
• Experience implementing SOC 2 controls in CI.
• Experience deploying and operating AI systems in regulated or highly controlled environments.
• Experience with OpenTelemetry, Prometheus, or Datadog.

Culture & Benefits

• Work on frontier AI research, expert datasets, reinforcement learning environments, and advanced benchmarks.
• Contribute to AI research and potentially showcase work at conferences including ICLR, ICML, and NeurIPS.
• Apply frontier AI innovation to enterprise business challenges.
• Collaborate with colleagues with experience at leading technology companies.
• Work in a fast-moving environment with startup-level speed, ownership, and impact.