[Remote] Machine Learning Engineer, Distributed vLLM

Note: The job is a remote job and is open to candidates in USA. Red Hat is the world’s leading provider of enterprise open source software solutions, and they are seeking a Machine Learning Engineer focused on distributed vLLM infrastructure. In this role, you will contribute to the design, development, and testing of new features for Red Hat AI Inference, collaborating on scalable inference systems and Kubernetes-native deployments.ResponsibilitiesContribute to the design, development, and testing of new features and solutions for Red Hat AI InferenceInnovate in the inference domain by participating in upstream communitiesDevelop and maintain distributed inference infrastructure leveraging Kubernetes APIs, operators, and the Gateway Inference Extension API for scalable LLM deploymentsDevelop and maintain system components in Go and/or Rust to integrate with the vLLM project and manage distributed inference workloadsDevelop and maintain KV cache-aware routing and scoring algorithms to optimize memory utilization and request distribution in large-scale inference deploymentsEnhance the resource utilization, fault tolerance, and stability of the inference stackDevelop and test various inference optimization algorithmsActively participate in technical design discussionsContribute to a culture of continuous improvement by sharing recommendations and technical knowledge with team membersCollaborate with other engineering and cross-functional teams to deliver on engineering deliverablesCommunicate effectively to team members to ensure proper visibility of development effortsBe taught, coached, and mentored by senior members of the teamProvide timely and constructive code reviewsSkillsStrong proficiency in Python and/or GoLang or similar languageExperience with cloud-native Kubernetes service mesh technologies/stacks such as Istio, Cilium, Envoy (WASM filters), and CNIWorking understanding of Layer 7 networking, HTTP/2, gRPC, and the fundamentals of API gateways and reverse proxiesKnowledge of serving runtime technologies for hosting LLMs, such as vLLM, SGLang, TensorRT-LLM, etcExcellent written and verbal communication skills, capable of interacting effectively with both technical and non-technical team membersAbility work independently in a dynamic, fast-paced environmentProficiency in C, C++, or RustExperience with the Kubernetes ecosystem, including core concepts, custom APIs, operators, and the Gateway API inference extension for GenAI workloadsWorking knowledge of high-performance networking protocols and technologies including UCX, RoCE, InfiniBand, and RDMA is a plusExperience with GPU performance benchmarking and profiling tools like NVIDIA Nsight or distributed tracing libraries/techniques like OpenTelemetryExperience in writing high performance code for GPUs and deep knowledge of GPU hardwareStrong understanding of computer architecture, parallel processing, and distributed computing conceptsBachelor's degree in computer science or related field is an advantage, though we prioritize hands-on experienceActive engagement in the ML research community (publications, conference participation, or open source contributions) is a significant advantageBenefitsComprehensive medical, dental, and vision coverageFlexible Spending Account - healthcare and dependent careHealth Savings Account - high deductible medical planRetirement 401(k) with employer matchPaid time off and holidaysPaid parental leave plans for all new parentsLeave benefits including disability, paid family medical leave, and paid military leaveAdditional benefits including employee stock purchase plan, family planning reimbursement, tuition reimbursement, transportation expense account, employee assistance program, and more!Company OverviewRed Hat is a software company that offers enterprise open-source software solutions. It is a sub-organization of IBM. It was founded in 1993, and is headquartered in Raleigh, North Carolina, USA, with a workforce of 10001+ employees. Its website is http://www.redhat.com.