Cloud-Scale Backend Engineer for ML Inference

Praxis, Inc.; San Francisco (CA); On-site; USD 170,000 - 250,000; Full time

Job summary

NomadicML in San Francisco is seeking a Backend / Infrastructure Engineer to join our platform that powers video intelligence. You’ll build scalable cloud ingestion, distributed GPU inference pipelines, and robust APIs/SDKs used by enterprises worldwide.

You’ll collaborate with ML researchers to productionize models, automate deployment, and improve reliability, speed, and developer experience across storage, scheduling, and orchestration.

Qualifications

• Backend systems and cloud experience for large-scale inference.
• Experience designing REST/gRPC APIs and developer-facing SDKs.
• Knowledge of asynchronous job orchestration frameworks.
• Hands-on with GPU inference scaling and distributed compute.
• Ability to productionize research-grade systems.

Responsibilities

• Build and scale the backbone powering NomadicML's video intelligence platform.
• Collaborate with ML researchers to productionize models and automate deployment.
• Expose capabilities via clean APIs/SDKs and improve observability.

Skills

Python

Go

TypeScript

Tools

AWS

GCP

Azure

Kubernetes

Docker

Ray

Dagster

Temporal

Job description

NomadicML in San Francisco is seeking a Backend / Infrastructure Engineer to join our platform that powers video intelligence. You’ll build scalable cloud ingestion, distributed GPU inference pipelines, and robust APIs/SDKs used by enterprises worldwide.

You’ll collaborate with ML researchers to productionize models, automate deployment, and improve reliability, speed, and developer experience across storage, scheduling, and orchestration.