Solutions Architect, Inference Deployments

NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s a unique legacy of innovation that’s fueled by great technology—and amazing people.

• →Lead architecture discussions with customers and co-design scalable inference systems with product and engineering teams. Define technical direction, integration milestones, and deployment plans across edge and cloud environments.
• →Deploy, test, and profile speech and action models for robotics and automation on edge devices. Optimize latency, throughput, and memory use within device constraints.
• →Lead optimization of synthetic data workflows spanning generation, augmentation, filtering, and data movement. Improve throughput and cost per usable output while preserving data quality.
• →Guide production inference deployments, including configuration, monitoring, capacity planning, performance testing, release validation, and rollback. Resolve complex issues across models, runtimes, and infrastructure.
• →Evaluate model optimization methods, including quantization, kernel selection, and batching. Validate application quality, explain performance tradeoffs, and use findings to inform product and engineering priorities.
• →Drive customer and field enablement through deployment recipes, demos, onboarding materials, and operating guides that help teams adopt and scale NVIDIA technologies.

• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field, or equivalent experience.
• 5+ years of professional experience in software or hardware engineering, developer relations, technical partnerships, solutions architecture, or product management, including 3+ years of direct, hands-on experience in AI inference or ML systems.
• Deep expertise in AI/ML and GPU inference, with a track record of driving product integrations and delivering production systems across edge or cloud environments.
• Hands-on experience building AI agents and working with Linux systems, containers, and at least one inference runtime or ML framework.
• Demonstrated expertise in performance profiling and production deployment, including monitoring and troubleshooting. Ability to design repeatable benchmarks that measure performance and application quality.
• Ability to explain complex technical concepts clearly to technical and non-technical audiences, from engineers to C-level executives.
• Strong problem-solving skills, intellectual curiosity, and a commitment to learning and helping customers resolve complex technical challenges.
• A track record of building trusted customer and partner relationships, balancing their needs, and guiding complex product and architecture decisions.

• Technical contributions that demonstrate clear approaches to complex problems and measurable improvements in performance or production reliability.
• A history of enabling customer adoption, with technical recommendations that influenced product or engineering decisions and delivered production results.
• Hands-on experience with NVIDIA Jetson, TensorRT Edge-LLM, Nemotron Speech, NVIDIA Riva, ROS 2, or NVIDIA Isaac in voice or robotics deployments.
• Experience with synthetic data generation or workflow orchestration using NVIDIA Cosmos or comparable tools.
• Experience with containerized inference, TensorRT-LLM, TensorRT, Triton Inference Server, vLLM, SGLang, or NVIDIA Dynamo.

NVIDIA is widely considered to be one of the technology world’s most desirable employers. We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you!

This posting is for an existing vacancy. 

NVIDIA uses AI tools in its recruiting processes.