Senior Platform Engineer: Scale Infra & AI Inference

openreqstaffing; New York (NY); Hybrid; USD 170,000 - 250,000; Full time

Benefits offered by this job

Competitive base salary

Equity participation

Medical, dental, and vision coverage

Flexible PTO

Hybrid NYC model

Remote considered for the right person

Job summary

Nomic is hiring a Senior Platform Engineer to own the infrastructure stack—multi-account AWS, Kubernetes, IaC, CI/CD—and to ensure production agents run fast, reliably, and at scale across many customer environments.

You will influence architectural decisions, scale the footprint across continents, and maintain high-performance, cost-effective services with strong security posture and observability.

Qualifications

• 5+ years in infrastructure, DevOps, or SRE roles running cloud infrastructure in production.
• Strong Kubernetes experience — deploying workloads and debugging real issues.
• Solid IaC skills — designing modules, managing state, blast radius considerations.
• Strong software fundamentals with production Python/TypeScript code, not just infra configs.
• Linux systems and networking fundamentals.
• CI/CD pipeline design and maintenance.
• Proactive orientation with wide surface area ownership.

Responsibilities

• Rollout and deployment across customer cloud environments with automated health checks and monitoring.
• Maintain fast, reliable, and cost-effective model inference at scale (infrastructure, GPU workloads).
• Oversee core infrastructure: Kubernetes, multi-account AWS, CI/CD, observability, DR, cost management.
• Strengthen security posture with access controls, secrets management, and vulnerability scanning.
• Define and evolve infrastructure through code—modular design and blast radius awareness.

Skills

Infrastructure

Kubernetes

IaC

Python/TypeScript

Linux

CI/CD

Proactive ownership

Tools

Terraform

Datadog

OpenTelemetry

PostgreSQL

Job description

Nomic is hiring a Senior Platform Engineer to own the infrastructure stack—multi-account AWS, Kubernetes, IaC, CI/CD—and to ensure production agents run fast, reliably, and at scale across many customer environments.

You will influence architectural decisions, scale the footprint across continents, and maintain high-performance, cost-effective services with strong security posture and observability.