Systems Software Engineer - AI and Cloud
Core
Design and implement agentic workflows with advanced AI techniques like RAG and LLMs, while evaluating cloud-native full-stack applications to power AI use cases.
Role type
Senior IC systems software engineer (AI inference & cloud)
Builds
Cloud-native inference systems and agentic AI workflows for NVIDIA products
Domain
AI/ML inference, cloud-native architecture, high-performance computing
Deliverable
production ML models
Required skills
Python, JavaScript, C++, microservices architecture, Kubernetes, API design, data structures, algorithms
Preferred skills
LLMs, modern AI software architecture, open-source contributions, Triton Inference Server, vLLM, TensorRT, edge deployment (via careerplan.io/jobs/JR2024087-systems-software-engineer-ai-and-cloud-at-nvidia)
Technologies
Kubernetes, vLLM, NVIDIA Triton Inference Server, TensorRT
Responsibilities
Evaluate cloud-native applications using microservices; Design and implement agentic workflows with RAG and LLMs; Analyze technical performance of AI solutions; Engage with cross-functional teams to improve product offerings; Develop developer-focused content including tutorials and code samples; Write technical whitepapers and run product demos
Seniority
Senior, hands-on IC
