Remote AI Infra DevOps Engineer - Scale & Observability

Linkup; United States; Hybrid; USD 110,000 - 170,000; Full time

Job summary

Linkup is seeking a top‑tier DevOps Engineer to work closely with the CTO and tech team on building and operating scalable AI‑powered web search infrastructure. You will design and maintain systems for indexing, retrieval, and monitoring, and automate deployment and observability across environments.

You’ll collaborate with ML and backend teams to streamline CI/CD and model deployment workflows, using AWS/GCP/Azure, Kubernetes, and Terraform in a fast‑paced startup setting.

Qualifications

• Experience with cloud infrastructure (AWS, GCP or Azure) and Kubernetes (2y minimum).
• Strong experience with distributed systems, networking, and infrastructure as code (Terraform).
• Ability to debug production issues and optimize infrastructure bottlenecks.

Responsibilities

• Build and operate large-scale, distributed systems powering AI-ready web search.
• Design, implement, and maintain infrastructure for indexing, retrieval, and monitoring.
• Automate deployment, scaling, and observability across all environments.
• Collaborate with ML and backend teams to streamline CI/CD and model deployment workflows.

Skills

Distributed systems

CI/CD

Observability

Networking

Cloud infrastructure

Kubernetes

Tools

Rust

Go

Node.js

Python

RocksDB

vLLM

Terraform

Kubernetes

AWS

GCP

Azure

Job description

Linkup is seeking a top‑tier DevOps Engineer to work closely with the CTO and tech team on building and operating scalable AI‑powered web search infrastructure. You will design and maintain systems for indexing, retrieval, and monitoring, and automate deployment and observability across environments.

You’ll collaborate with ML and backend teams to streamline CI/CD and model deployment workflows, using AWS/GCP/Azure, Kubernetes, and Terraform in a fast‑paced startup setting.