Backend Engineer – Multi-Cloud Inference Platform (Remote)

Modular Inc; Los Altos (CA); Remote; USD 148,000 - 324,000; Full time

Benefits offered by this job

Amazing team

World-class benefits

Competitive compensation

Team building events

Job summary

Modular is seeking an experienced backend engineer to shape end-to-end distributed inference deployments on a multi-cloud platform. You will build scalable services, improve observability, and drive performance across diverse hardware and cloud providers.

The team emphasizes secure multi-tenant infrastructure, Kubernetes-based deployments, and close collaboration with product and ML teams. Remote-friendly role with offices in Los Altos, CA.

Qualifications

• 5+ years of backend engineering experience.
• Experience with service-oriented architecture and distributed systems.
• Experience with cloud providers (AWS, GCP, Azure, neoclouds).
• Experience with Kubernetes and operating your own services.
• Passion for building high-performance, low-toil, observable systems.
• Experience in machine learning technologies and use cases.
• Strong teamwork and alignment with Modular culture.
• Practical security in multi-tenant environments.
• Experience in high-scale ML inference infrastructure.
• Familiarity with Go (Golang).

Responsibilities

• Build the multi-cloud, multi-tenant platform powering Modular’s inference services.
• Build fault-tolerant, low toil services across varied hardware platforms and clouds.
• Push observability, multi-cloud deployments, cold-start optimizations.
• Build helm charts, kubernetes operators to simplify deployments.

Skills

Backend engineering

Distributed systems

ML inference

Security in multi-tenant

Observability

Team collaboration

High performance systems

Cloud architecture

Go (Golang)

Tools

AWS

GCP

Azure

neoclouds

Kubernetes

Go

Job description

Modular is seeking an experienced backend engineer to shape end-to-end distributed inference deployments on a multi-cloud platform. You will build scalable services, improve observability, and drive performance across diverse hardware and cloud providers.

The team emphasizes secure multi-tenant infrastructure, Kubernetes-based deployments, and close collaboration with product and ML teams. Remote-friendly role with offices in Los Altos, CA.