Senior Developer Technology Engineer - Edge Agentic AI
Core
Enable professional agentic AI workflows at the edge powered by NVIDIA RTX and DGX platforms by solving local end-to-end GPU deployment challenges and optimizing runtime performance.
Role type
Senior IC developer technology engineer (edge agentic AI)
Builds
Open-source software (GGML, Llama.cpp, Ollama, vLLM, ONNX Runtime) and efficient end-to-end agentic AI deployment solutions
Domain
AI/ML, GPU computing, Edge computing
Deliverable
production ML models
Required skills
C/C++, Python, CUDA, GPU profiling and debugging, software design, Linux/Windows development
Preferred skills
TensorRT-RTX, cuDNN, NVIDIA Model Optimizer, NPU/ARM architecture deployment, professional agentic AI use cases
Technologies
RTX, DGX, GGML, Llama.cpp, Ollama, vLLM, ONNX Runtime, CUDA, Nsight, TensorRT-RTX, cuDNN, Model Optimizer
Responsibilities
Solve local end-to-end agentic AI GPU deployment challenges; Apply profiling and debugging tools to analyze accelerated workflows; Conduct hands-on trainings and develop sample code; Improve LLM & GenAI user experience via OSS software enhancements; Collaborate with GPU driver and architecture teams; Provide technical leadership and mentorship to junior engineers
Seniority
Senior, hands-on IC with mentorship responsibilities
