Senior Software Engineer - Red Hat Ai Inference Server (emea) - Q2 Role
Red Hat
Fully remote
Vllm and llm-compressor
Devops and ci/cd infrastructure
Python and pytest proficiency
Red Hat is on a mission to bring the power of open-source LLMs and vLLM to every enterprise, accelerating AI for the enterprise and bringing operational simplicity to GenAI deployments
Job Summary
Red Hat is on a mission to bring the power of open-source LLMs and vLLM to every enterprise, accelerating AI for the enterprise and bringing operational simplicity to GenAI deployments.
The role involves building and releasing the Red Hat AI Inference Server, continuously improving DevOps processes and tooling, and automating procedures.
Red Hatters are encouraged to bring their best ideas, no matter their title or tenure, in an open and inclusive environment that drives innovation.
Matching Summary
Red Hat is on a mission to bring the power of open-source LLMs and vLLM to every enterprise, accelerating AI for the enterprise and bringing operational simplicity to GenAI deployments.
Skills & Requirements
Must-have
vLLM and llm-compressor
DevOps and CI/CD infrastructure
Python and PyTest proficiency
Kubernetes/OpenShift administration
Cloud Computing (AWS, GCP, Azure, IBM Cloud)
Nice-to-have
contributing to vLLM CI community
open and inclusive environment
solving challenging technical problems
Key Requirements
2+ years of experience in MLOps, DevOps, Automation
Experience with Release Engineering
Experience evaluating LLMs for performance and accuracy
Strong experience with Git, Github Actions, BuildKite, Terraform, Jenkins, Ansible
Experienced with administering Kubernetes/OpenShift and/or docker/podman