Senior Developer Technology Engineer, Edge Agentic AI

What you'll do

• Solve end-to-end agentic AI GPU deployment challenges on NVIDIA RTX and DGX platforms.
• Use profiling and debugging tools to identify and resolve performance bottlenecks in accelerated AI workflows.
• Develop sample code, conduct training sessions, and host presentations regarding efficient AI deployment.
• Enhance LLM and GenAI user experiences by improving open-source software like GGML, Llama.cpp, and vLLM.
• Provide feedback to GPU architecture teams to influence next-generation hardware features based on real-world workflows.
• Provide technical leadership and mentorship to junior engineers within the team.

What we're looking for

• A Bachelor's or Master's degree in Computer Science, Engineering, or a related field is required.
• Candidates must have at least 5 years of professional experience in local GPU deployment, profiling, and optimization.
• Proficiency in C/C++, Python, software design, and programming techniques is required.
• Experience with Windows and Linux development environments is required.
• Experience with CUDA and NVIDIA's Nsight GPU profiling and debugging suite is required.
• Preferred experience includes GPU-accelerated AI inference using TensorRT-RTX, cuDNN, and NVIDIA Model Optimizer.
• Preferred expertise in open-source LLM/GenAI software (e.g., GGML, Llama.cpp, Ollama, vLLM) and agentic AI workflows.
• Knowledge of GPU architectures, NPU deployment, and ARM architectures is preferred.