LLM Inference Architect - GPU Performance & Tools (Equity)

NVIDIA Corporation is seeking a Deep Learning Architect specializing in LLM Inference for New College Grads in Santa Clara, California. The role involves optimizing performance for Large Language Models, developing profiling tools, and collaborating on benchmarking methodologies. Candidates should have a Master's or PhD in a relevant field, experience in software development, and deep learning expertise. Competitive salary ranges from $124,000 to $241,500 based on experience. Equity is also part of the compensation package.
#J-18808-Ljbffr