Nvidia Solutions Architect AI ML 

United States, Texas 

378124734

What you will be doing:

• Help cloud customers craft, deploy, and maintain scalable, GPU-accelerated inference pipelines on cloud ML services and Kubernetes for large language models (LLMs) and generative AI workloads.

• Enhance performance tuning usingTensorRT/TensorRT-LLM,vLLM, Dynamo, and Triton Inference Server to improve GPU utilization and model efficiency.

• Collaborate with multi-functional teams (engineering, product) and offer technical mentorship to cloud customers implementing AI inference at scale.

• Build custom PoCs for solution that address customer’s critical business needs applying NVIDIA hardware and software technology

• Partner with Sales Account Managers or Developer Relations Managers to identify and secure new business opportunities for NVIDIA products and solutions for ML/DL and other software solutions

• Prepare and deliver technical content to customers including presentations about purpose-built solutions, workshops about NVIDIA products and solutions, etc.

• Conduct regular technical customer meetings for project/product roadmap, feature discussions, and intro to new technologies. Establish close technical ties to the customer to facilitate rapid resolution of customer issues

What we need to see:

• BS/MS/PhD in Electrical/Computer Engineering, Computer Science, Statistics, Physics, or other Engineering fields or equivalent experience.

• 3+ Years in Solutions Architecture with a proven track record of moving AI inference from POC to production in cloud computing environments including AWS, GCP, or Azure

• 3+ years of hands-on experience with Deep Learning frameworks such as PyTorch and TensorFlow

• Excellent knowledge of the theory and practice of LLM and DL inference

• Strong fundamentals in programming, optimizations, and software design, especially in Python

• Experience with containerization and orchestration technologies like Docker and Kubernetes, monitoring, and observability solutions for AI deployments

• Knowledge of Inference technologies - NVIDIA NIM, TensorRT-LLM, Dynamo, Triton Inference Server, vLLM, etc

• Proficiency in problem-solving and debugging skills in GPU environments

• Excellent presentation, communication and collaboration skills

Ways to stand out from the crowd:

• AWS, GCP or Azure Professional Solution Architect Certification.

• Experience optimizing and deploying large MoE LLMs at scale

• Active contributions to open-source AI inference projects (e.g., vLLM, TensorRT-LLM Dynamo, SGLang, Triton or similar)

• Experience with Multi-GPU Multi-node Inference technologies like Tensor Parallelism/Expert Parallelism, Disaggregated Serving, LWS, MPI, EFA/Infiniband, NVLink/PCIe, etc

• Experience in developing and integrating monitoring and alerting solutions using Prometheus, Grafana, and NVIDIA DCGM and GPU performance Analysis and tools like NVIDIA Nsight Systems