Jobrapido
Jacksonville / Global
GET
The Big Jobsite
You have blocked notifications
Oops! You have blocked notifications. Click here for more info
You have blocked notifications, please check your browser settings.
You're currently subscribed to job notifications
Subscribe to notifications
You will no longer receive notifications
Jacksonville / Global
Optomi , in partnership with a large telecommunications company, is seeking a Principal Software Engineer to join their team in the Bedminster, NJ Area. The ideal candidate will have experience building, deploy, and scale production AI inference infrastructure. You’ll work across Kubernetes, vLLM, Python, GPUs, and cloud/on-prem environments to make model serving reliable, scalable, and highly automated.
What The Right Professional Will Enjoy
Building and operating LLM inference infrastructure at scale.
Deploying and managing models using vLLM and Kubernetes.
Developing Python automation for model deployment, scaling, updates, rollbacks, and health monitoring.
Managing GPU capacity, performance, reliability, and production workloads.
Building tools that allow engineering teams to deploy and access models without managing underlying infrastructure.
Supporting both R&D and production inference environments.
Troubleshooting and optimizing model-serving performance and reliability.
Remote flexibility
Apply Today If Your Background Includes
Strong software engineering and Python skills.
Deep hands-on Kubernetes experience.
Production experience with LLM inference/model serving, ideally vLLM.
Experience with GPU infrastructure (Not required), containers, and CI/CD.
Understanding of scaling, automation, observability, and reliability for distributed systems.
Experience with cloud and/or on-prem infrastructure preferred.
Jacksonville / Global
Jacksonville / Global
Jacksonville / Global
Jacksonville / Global
Jacksonville / Global
Jacksonville / Global