Distinguished Engineer, Scaled Out Inferencing

What you'll do

• Architect high-throughput, low-latency distributed pipelines for massive-scale AI inference workloads.
• Define and drive the technical roadmap for full-lifecycle model management including deployment, versioning, and automated scaling.
• Perform hardware-software co-optimization by tuning performance at the kernel and driver levels to optimize GPU resource management.
• Guide and influence open-source projects like TensorRT-LLM, vLLM, and SGLang to improve inference on NVIDIA hardware.
• Establish systems and orchestration layers to ensure advanced AI models run with peak efficiency on accelerated computing hardware.
• Design and manage the full software lifecycle from initial architecture and development to deployment and operations.
• Collaborate with customers and infrastructure providers to establish industry standards for performance and availability.

What we're looking for

• Experience in technical roles with a focus on AI infrastructure and large-scale inference orchestration.
• 7 to 10+ years of leadership experience.
• BS/MS or higher degree in systems engineering, software engineering, or related fields.
• Proficiency in GPU architecture, hardware acceleration, and low-level performance tuning including CUDA and kernels.
• Proven track record building secure, highly available, and durable production distributed systems.
• Ability to synthesize cross-functional needs into architecture while guiding execution across diverse teams.
• Experience designing and operating scaled-out systems in enterprise and cloud environments (preferred).
• Familiarity with open source ecosystems such as Dynamo, TensorRT-LLM, vLLM, SGLang, Ray, Linux, and Kubernetes (preferred).