Senior Deep Learning Software Engineer, Inference
Description For Senior Deep Learning Software Engineer, Inference
NVIDIA is seeking a Senior Deep Learning Software Engineer specializing in inference optimization to join their growing team. This role sits at the intersection of cutting-edge AI technology and high-performance computing, where you'll be instrumental in developing and optimizing GPU-accelerated software that powers sophisticated AI applications.
The position involves working with advanced deep learning frameworks like SGLang and vLLM, which are crucial for efficient large-scale model serving and inference. You'll be responsible for implementing and optimizing state-of-the-art LLM and Generative AI models across NVIDIA's range of accelerators, from datacenter GPUs to edge SoCs.
As a senior engineer, you'll collaborate with the deep learning community to implement cutting-edge algorithms and drive performance improvements. The role requires expertise in C/C++ programming, deep learning frameworks, and GPU optimization techniques. You'll work with tools like CUTLASS, OAI Triton, NCCL, and CUDA kernels to build and optimize model serving pipelines.
The position offers a competitive salary range of $148,000 to $287,500 USD, along with equity and comprehensive benefits. NVIDIA is known for being one of the technology world's most desirable employers, offering opportunities to work on groundbreaking AI technologies that transform industries.
This role is perfect for someone with 5+ years of relevant experience, strong programming skills, and a deep understanding of AI/ML technologies. You'll be joining a forward-thinking team at NVIDIA's Santa Clara location, where you'll have the opportunity to impact the future of AI acceleration and inference optimization.
The ideal candidate will have a Masters or PhD in a relevant field, experience with deep learning model optimization, and a track record of contributing to significant software projects. Experience with multi-GPU communications and performance optimization would be particularly valuable.
Responsibilities For Senior Deep Learning Software Engineer, Inference
- Performance optimization, analysis, and tuning of DL models in various domains like LLM, Multimodal and Generative AI
- Scale performance of DL models across different architectures and types of NVIDIA accelerators
- Contribute features and code to NVIDIA's inference libraries, vLLM and SGLang, FlashInfer and LLM software solutions
- Work with cross-collaborative teams across frameworks, NVIDIA libraries and inference optimization innovative solutions
Requirements For Senior Deep Learning Software Engineer, Inference
- Masters or PhD or equivalent experience in relevant field (Computer Engineering, Computer Science, EECS, AI)
- 5+ years of relevant software development experience
- Excellent C/C++ programming and software design skills
- Software Agile skills and Python experience
- Experience with training, deploying or optimizing the inference of DL models in production
- Background with performance modeling, profiling, debug, and code optimization
- GPU programming experience (CUDA, OAI TRITON or CUTLASS)
Benefits For Senior Deep Learning Software Engineer, Inference
- Equity
- Competitive base salary
Jobs Related To NVIDIA Senior Deep Learning Software Engineer, Inference
