AI Embedded Engineer (Sunnyvale)

Responsibilities Design and develop high-performance AI frameworks for large-scale distributed computation Optimize scalability and efficiency using Nvidia Dynamo Framework Work with distributed dataflow programming to orchestrate GPU workloads using Python and Kubernetes Integrate advanced LLMs into real-world applications, shaping the future of AI-driven software Contribute to building test-automation infrastructure for Kubernetes on large-scale GPU clusters. Help develop detailed test plans for different milestones and operationalize them in test-automation infrastructure. Own and conduct end-end system, scale and stress testing. Working together with SW leads and Technical Program Manager, qualify the releases. Attract and help build downstream production engineering talent. Role model and foster a culture of humility and innovation for product delivery. Experience: 38+ years of experience in software engineering, ideally at a staff level Strong expertise in distributed dataflow programming and distributed systems Hands-on experience with LLMs and AI frameworks Proficiency in Python, with experience orchestrating GPU workloads Experience with Kubernetes for containerized application deployment and orchestration Experience working in systems & systems SW, Cloud and Kubernetes. Experience with production-testing and automation of Kubernetes deployments. Preferred Qualifications: Master's or similar qualification in a relevant field. Experience with scalable test and automation infrastructure to productionize workloads. Experience with GPU platforms (e.g., Nvidia DGX, H100) and high-performance computing environments. Experience triaging customer bugs, prioritizing, and resolving issues in production. Familiarity with AI developer frameworks, tools, and automation systems