Inference Systems Engineer — Scale GPU Fleets & Scheduling

Luma; Seattle (WA); On-site; USD 195,000 - 345,000; Full time

Job summary

Luma in Seattle, WA is hiring a systems-focused engineer to own how models are served at scale. You’ll integrate new architectures into the inference engine, scale deployments across thousands of machines, and optimize GPU resource usage while meeting SLOs.

You’ll work across research, engineering, and infrastructure, building tooling to measure and track inference jobs, and maintaining robust CI/CD for model checkpoints and SDKs. This is a systems role, not pure modeling.

Qualifications

• Experience building and operating large-scale inference systems.
• Proven ability to deploy and monitor model serving at scale.
• Familiarity with scheduling, traffic control, and fleet management.
• Hands-on experience with Docker, Kubernetes, and cloud storage.

Responsibilities

• Own the integration of new model architectures into the inference engine.
• Scale deployments across thousands of machines and multiple clusters.
• Collaborate with research, engineering, and infra to improve efficiency.
• Build tooling to measure, profile, and track inference jobs lifecycles.
• Automate and maintain inference services for uptime and reliability.
• Guide CI/CD for model checkpoints and SDKs; optimize GPU usage.

Skills

Python

System architecture

Model serving

Queues and scheduling

Linux

Tools

Docker

Kubernetes

Redis

S3-compatible storage

Job description

Luma in Seattle, WA is hiring a systems-focused engineer to own how models are served at scale. You’ll integrate new architectures into the inference engine, scale deployments across thousands of machines, and optimize GPU resource usage while meeting SLOs.

You’ll work across research, engineering, and infrastructure, building tooling to measure and track inference jobs, and maintaining robust CI/CD for model checkpoints and SDKs. This is a systems role, not pure modeling.