Used Tools & Technologies
Not specified
Required Skills & Competences ?
Python @ 6 Algorithms @ 7 Data Structures @ 7 Debugging @ 7 PyTorch @ 7 CUDA @ 4 GPU @ 4Details
NVIDIA’s Deep Learning Architecture and Libraries Group is seeking a software engineer to advance performance analysis and profiling capabilities for deep learning workloads. You will collaborate with GPU architects, CUDA developers, and performance engineers to design, implement, and integrate innovative profiling and monitoring features into internal tooling that accelerate AI system performance across domains such as autonomous vehicles and supercomputing.
Responsibilities
- Analyze, profile, and optimize deep learning workloads on state-of-the-art hardware and software platforms.
- Design and develop tools, techniques, and workflows for profiling and analysis of deep learning workloads.
- Work with multi-disciplinary teams to design, implement, and verify new profiling and monitoring features, often leveraging new hardware capabilities.
- Define software/hardware metrics for performance analysis of deep learning workloads and validate them for upcoming architectures.
- Continuously learn and apply the latest techniques and frameworks for deploying and optimizing AI/DL workloads to improve the efficiency and effectiveness of internal tools.
Requirements
- Bachelor’s, Master’s, or PhD in a relevant field (e.g., Computer Science, Electrical Engineering, Computer Engineering) or equivalent experience.
- 8+ years of relevant experience (including graduate work if applicable).
- Proficiency in C++ and Python.
- Experience with deep learning frameworks (examples listed: PyTorch, JAX, TRT, ONNX, Triton) and a strong understanding of deep learning fundamentals.
- Strong computer science fundamentals: algorithms, data structures, optimization, debugging, operating systems, and parallel computing.
Ways to Stand Out
- Experience with performance analysis of AI training/inference applications.
- Knowledge of device drivers and/or compiler implementation.
- Knowledge of GPU and/or CPU architecture and general computer architecture principles.
Compensation & Benefits
- Base salary range: 184,000 USD - 287,500 USD (determined based on location, experience, and comparable roles).
- Eligible for equity and company benefits (see NVIDIA benefits).
Other Information
- Applications for this job will be accepted at least until August 5, 2025.
- NVIDIA is an equal opportunity employer committed to fostering a diverse work environment and does not discriminate on the basis of protected characteristics.