Distinguished Engineer, Scaled Out Inferencing
Core
Lead the development of global strategy for scaled-out AI inferencing, architecting high-throughput, low-latency distributed pipelines and model serving strategies for massive scale and production reliability.
Role type
Distinguished Engineer, Scaled Out Inferencing
Builds
Distributed inference systems, model serving strategies, orchestration layers for AI models on accelerated computing hardware
Domain
AI Infrastructure, High-Performance Computing, Cloud & Enterprise Environments
Deliverable
production ML models
Required skills
Distributed systems architecture, GPU architecture, hardware acceleration, low-level performance tuning (CUDA, kernels), cloud-native architectures, automated scaling, open source ecosystem influence, technical leadership, cross-functional alignment
Preferred skills
AI/ML workload system design, secure highly available scaled-out systems, scalable process creation, open source project governance
Technologies
CUDA, TensorRT-LLM, vLLM, SGLang, Dynamo, Ray, Kubernetes, Linux
Responsibilities
Architect distributed pipelines for high-throughput, low-latency inference; drive hardware-software co-optimization and kernel-level performance tuning; guide open source projects (Dynamo, TensorRT-LLM, vLLM, SGLang); orchestrate full-lifecycle model management including automated deployment and scaling; engage stakeholders to set industry standards for performance and availability; lead technical planning and evolution of large-scale technical scope
Seniority
Distinguished, Strategy & Mentorship
