Senior Software Engineer, AI Inference

Job Summary

At Red Hat, we believe the future of AI is open and we are on a mission to bring the power of open‑source LLMs and vLLM to every enterprise. The Red Hat AI Inference team accelerates AI for the enterprise and brings operational simplicity to GenAI deployments. As leading developers and maintainers of the vLLM project, and inventors of state‑of‑the‑art techniques for model compression, our team provides a stable platform for enterprises to build, optimize, and scale LLM deployments.

We are seeking an experienced Senior Software Engineer to build and release the Red Hat AI Inference Server. You will own the full lifecycle, from compiling vLLM wheels across multiple hardware backends and architectures, to packaging enterprise‑grade container images, managing multi‑cloud infrastructure, and validating LLM accuracy and performance across a growing matrix of models and hardware.

• Build and release vLLM wheels across multiple hardware backends and CPU architectures, managing complex native dependency chains including PyTorch, Triton, and other accelerator‑specific libraries.
• Design and maintain CI/CD pipelines spanning multiple platforms including Git Hub Actions, Git Lab CI, and Buildkite for build, test, and release workflows.
• Manage and scale multi‑cloud GPU infrastructure using Terraform and Ansible, including both bare‑metal and Kubernetes‑based compute runners.
• Own the model validation pipeline, orchestrating accuracy evaluation, performance benchmarking, tool‑calling validation, and smoke testing across dozens of LLMs on both bare metal and Open Shift.
• Develop and maintain the Python tooling and automation that powers the build, packaging, validation, and release processes.
• Drive adoption of agentic AI and intelligent automation to streamline engineering workflows, accelerate debugging, and reduce toil across the team.

• 5+ years of software engineering experience with significant depth in build systems, release engineering, or infrastructure.
• Strong Python development skills with experience building well‑tested, maintainable tooling and automation.
• Hands‑on experience building and packaging Python projects with native compiled extensions, including familiarity with C++ and CUDA build tool chains, wheel packaging, and multi‑architecture builds.
• Deep familiarity with container ecosystems, including Dockerfiles, Containerfiles, image registries, and container build pipelines.
• Understanding of LLM evaluation methodology, including accuracy benchmarks such as MMLU, GSM8K, and Hella Swag, as well as inference performance metrics like throughput and latency.
• Experience with CI/CD platforms such as Git Hub Actions, Git Lab CI, Tekton, or Buildkite.
• Solid understanding of release engineering practices including reproducible builds, artifact management, dependency pinning, and security scanning.
• Experience with infrastructure‑as‑code tools such as Terraform and Ansible, and managing cloud resources at scale.
• Working knowledge of Kubernetes and/or Open Shift for deploying and testing workloads.
• Enthusiasm for applying LLM‑based agents and AI‑assisted tools to automate engineering workflows, with a track record of identifying repetitive processes and replacing them with intelligent automation.
• Excellent communication skills, capable of interacting effectively with both technical and non‑technical team members.
• A Bachelor's or Master's degree in computer science, computer engineering, or a related field. A Ph.D. in an ML‑related domain is a significant advantage.
• Contributions to upstream open‑source projects, particularly vLLM, PyTorch, or other AI/ML infrastructure.
• Experience with GPU‑accelerated workloads and building software for heterogeneous hardware.
• Familiarity with LLM inference serving, model optimization, quantization techniques, or evaluation frameworks.
• Proficiency in C#.

Salary range: $ – $. Actual offer will be based on your qualifications. This position may also be eligible for bonus, commission, and/or equity. For positions with Remote‑US locations, the actual salary range may differ based on location but will be commensurate with job duties and relevant work…