Platform Engineer - GPU Kubernetes

About Us

At Reactor, our mission is to unlock a future where anyone can create
interactive media applications
that delight, educate, and simulate. We're building a new kind of platform for
real-time generative media
, enabling developers to go from idea to immersive, dynamic experience in seconds.

We're a small, focused team of YC and unicorn founders and senior engineers with deep expertise in 3D, generative video, developer platforms, and creative tools. We aspire to continuously push the boundaries of what's possible: if you're driven to do the same, we'd love to hear from you. www.reactor.inc.

About the role

We’re looking for a
Senior Platform Engineer
to own and scale the infrastructure powering our AI models in production.

This is
not a typical DevOps role
. You’ll work across:

• GPU orchestration
• Multi-cloud Kubernetes
• Real-time networking
• Observability at scale

You’ll be the person who can answer:

• Why did a model pod take 4 minutes to schedule?
• Why did cross-region latency spike?
• Why are packets dropping in a media relay?

What You’ll Do

- Run and scale
multi-region Kubernetes clusters
across AWS and GPU cloud providers
- Own
GitOps workflows
(Helm, Kustomize, image automation, CD)
- Manage
GPU infrastructure
(scheduling, caching, cold-start optimization, observability)
- Improve
networking systems
(ingress, load balancing, cross-region connectivity)
- Build a robust
observability stack
(metrics, logs, traces, profiling)
- Maintain
infra security
(IAM, secrets, certificates, encryption)
- Own CI/CD across a
monorepo (Go + Python + Helm)
- Partner with ML engineers on
model serving and performance tuning

What We’re Looking For

- Deep experience running
Kubernetes in production at scale
- Strong
infrastructure-as-code
(Terraform, Pulumi, etc.)
- Hands-on experience with
GPU workloads on Kubernetes
- Familiarity with
GitOps tools
(ArgoCD, FluxCD)
- Solid understanding of
observability systems
- Strong
networking fundamentals
(TLS, DNS, load balancing)
- Experience owning infrastructure
end-to-end in a startup environment

Nice to Have

• Experience with GPU cloud providers (CoreWeave, Lambda Labs, Crusoe, etc.)
• Real-time media / streaming systems
• Go or Python
• ML model serving + GPU runtime optimization
• FinOps / GPU cost optimization

Not a Fit If

• You’ve only worked on CI/CD without running clusters
• Your experience is limited to managed PaaS (Heroku, Vercel, etc.)
• You need tightly defined scope vs figuring out what to build next

Logistics

- Based
in-person in San Francisco
- Visa sponsorship + relocation support available

Benefits

• Competitive SF salary + meaningful early equity
• Health, dental, and vision coverage