Senior Inference Technical Product Marketing Manager - Accelerated Computing

Help drive NVIDIA's inference platform technical go-to-market efforts Work closely with engineering and product management teams to understand key technical capabilities of our inference stack from GPUs, CPUs, networking, CUDA libraries, model architectures and deployment techniques (e.g.parallelisms, configurations, etc.) Diligently review and remain up to date on model architectures, frameworks, arxiv papers, whitepapers deployment techniques (e.g.disaggregated serving, KV cache implementations) and identify intersection points between the latest AI models and NVIDIA's platform to maximize performance and minimize TCO Develop crisp clear positioning, messaging and assets to highlight NVIDIA's leadership position in inference. Assets (blogs, whitepapers, presentations, analyst briefings, seminars at developer conferences) Closely follow competitive inference announcements and prepare appropriate responses for business and technical/developer audiences Assist on building keynote slides for executives for areas that you're a subject matter expert Ability to present to executive audiences Experience developing LLM models Experience working with hyperscale cloud providers