24 hours ago
Base Salary
$224k - $357k/yr
Responsibilities
- Analyze, debug, and optimize customer and partner deep learning models on NVIDIA platforms at the operator and kernel level.
- Own performance benchmarking for MLPerf Edge, industry benchmarks, and partner engagements, including methodology and reproducibility.
- Evaluate emerging deep learning architectures for compilation feasibility, memory footprint, and latency on target systems-on-chip.
- Collaborate with compiler, runtime, hardware, automotive, and robotics teams to connect model insights with platform capabilities.
- Contribute to build reviews and internal roadmap priorities based on customer workload patterns.
- Represent NVIDIA’s deep learning optimization expertise at conferences, webinars, and partner events.
- Build and deploy inference solutions using TensorRT and related compiler technologies on Jetson, DRIVE, and GPU plus ARM platforms.
- Develop Proofs of Readiness and collaborate with compiler teams on Torch-TRT, MLIR-TRT, and related frameworks.
Requirements
- Master’s degree or equivalent experience in Computer Science, Electrical Engineering, or a related field.
- Over 12 years of industry experience, including at least 8 years specializing in deep learning model optimization, inference engineering, or neural network compilation.
- Over 5 years of embedded or edge software experience delivering production inference solutions in power-limited and latency-sensitive environments.
- Expertise reviewing deep learning architectures at the operator and kernel level, including transformers, attention variants, vision encoders, multimodal or vision-language models, diffusion models, and state space models.
- Expert knowledge of GPU architecture, CUDA, heterogeneous computing, TensorRT, compiler intermediate representations, and low-level performance optimization.
- Understanding of QNX/Linux internals, memory management, C/C++, embedded software, and systems software concepts.
- Experience with parallel programming such as CUDA or OpenMP and with memory hierarchies, data movement, and compute utilization.
- Demonstrated ability to work directly with external technical customers and partners to solve production workload and performance issues.
- Preferred experience with TVM, MLIR, XLA, Triton, inference runtime development, autonomous vehicle perception or planning stacks, MLPerf, physical AI models, and automotive safety standards including ISO 26262 and SOTIF.
Benefits
- Eligible for equity and benefits.
- Base salary is determined by location, experience, and comparable employee pay; the stated base salary range is USD 224,000–356,500 per year.
- Applications will be accepted at least until October 18, 2026.
Categories
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.