Senior Deep Learning Software Engineer, Inference
About the role
then paragraph. We need to preserve all substantive info: description of role, responsibilities bullet list, requirements bullet list, ways to stand out bullet list (maybe under Skills or Qualifications). Could treat "Ways to Stand out from The Crowd" as additional qualifications/skills. Could put under Skills. We need to use- for any list of duties/requirements/benefits. So each bullet list becomes ul li.
We need
for prose. We must not include filler like "commensurate with experience". Not present. We must not include duplicated lines. Let's extract content. Intro: "NVIDIA seeks a Senior Software Engineer specializing in Deep Learning Inference for our growing team. As a key contributor, you will help design, build, and optimize the GPU-accelerated software that powers today’s most sophisticated AI applications. Our team is responsible for developing and maintaining high-performance open-source frameworks, which are at the forefront of efficient large-scale model serving and inference. You will play a central role in improving these platforms, facilitating smooth deployment and serving of groundbreaking language models. You’ll work closely with the deep learning community to implement the latest algorithms for public release in inference frameworks. Your work will focus on identifying and driving performance improvements for state-of-the-art LLM and Generative AI models across NVIDIA accelerators, from datacenter GPUs to edge SoCs. You'll bring to bear open-source tools and plugins—including CUTLASS, OAI Triton, NCCL, and CUDA kernels—to implement and optimize model serving pipelines." That's About the role. Responsibilities (What You'll Be Doing): bullet list: - 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. We need to keep exactly as given. Requirements (What We Need To See): bullet list: - Masters or PhD or equivalent experience in relevant field (Computer Engineering, Computer Science, EECS, AI). - 5+ years of relevant software development experience. - You'll need excellent C/C++ programming and software design skills. - SW Agile skills are helpful and Python experience is a plus. - Prior experience with training, deploying or optimizing the inference of DL models in production is a plus. - Prior background with performance modeling, profiling, debug, and code optimization or architectural knowledge of CPU and GPU is a plus. - GPU programming experience (CUDA, OAI TRITON or CUTLASS) is a plus. Note: "SW Agile" maybe "SW Agile skills". Keep. Ways to Stand out from The Crowd: bullet list: - Contribute to deep learning software projects, such as PyTorch, vLLM, and SGLang to drive advancements in the field. - Experience with Multi GPU Communications (NCCL, NVSHMEM) We could put these under Skills or Qualifications. Since they are additional qualifications, maybe under Skills. Benefits: "With highly competitive salaries and a comprehensive benefits package, 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 and, due to outstanding growth, our special engineering teams are growing fast. If you're a creative and autonomous engineer with a genuine passion for technology, we want to hear from you! ... You will also be eligible for equity and benefits." We need to extract benefits: comprehensive benefits package, equity. Also mention forward-thinking people etc but that's fluff. Keep substantive: comprehensive benefits package, equity. Pay: salary ranges: base salary range 152,000 USD - 241,500 USD for Level 3, and 184,000 USD - 287,500 USD for Level 4. Also mention base salary determined based on location, experience, and pay of employees in similar positions. Also equity. Schedule: none. We must not include application instructions like "Applications for this job will be accepted at least until August 31, 2026." Remove. Also remove "This posting is for an existing vacancy." etc. Also remove EEO statements. Now produce HTML. Structure:
About the role
...
Responsibilities
- ... ...
Requirements
- ... ...
Skills
- ... ...
Benefits
- Comprehensive benefits package
- Eligibility for equity
Pay
Base salary range: $152,000 USD – $241,500 USD for Level 3; $184,000 USD – $287,500 USD for Level 4. Salary is determined based on location, experience, and market pay for similar positions.
We need to preserve exact numbers and phrasing? The instruction: Preserve ALL substantive information; do NOT invent or summarize away detail. So we should keep the exact wording as much as possible, but we can rephrase slightly? Better to keep original phrasing. Original: "With highly competitive salaries and a comprehensive benefits package, 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 and, due to outstanding growth, our special engineering teams are growing fast. If you're a creative and autonomous engineer with a genuine passion for technology, we want to hear from you! Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 152,000 USD - 241,500 USD for Level 3, and 184,000 USD - 287,500 USD for Level 4. You will also be eligible for equity and benefits." We can keep that as prose in Benefits and Pay sections. But we need to split benefits and pay. Benefits: comprehensive benefits package, equity. Pay: salary ranges and determination. We could keep afor Benefits: "NVIDIA offers a comprehensive benefits package and eligibility for equity." But that is summarizing. Might be okay as it's not inventing; it's derived. However instruction: do NOT invent or summarize away detail. Summarizing may be considered summarizing away detail? It's okay to combine but we must not lose detail. The detail includes "comprehensive benefits package" and "eligibility for equity". That's captured. The fluff about forward-thinking people etc can be omitted as it's not substantive? It's somewhat fluff but maybe considered boilerplate? It's not required to keep. The instruction: Remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. The fluff about forward-thinking people is not boilerplate but could be considered marketing fluff. Might be okay to keep? But we need to preserve ALL substantive information. Is that substantive? It's more promotional. Might be considered not essential. Safer to keep it? But we need to avoid filler. The instruction: Prefer a few substantive sections over many thin ones. So we can keep a short paragraph about benefits and equity. Let's keep Benefits section as:
NVIDIA offers a comprehensive benefits package and eligibility for equity.
That captures the substantive benefit info. Pay section: keep the exact sentences about base salary determination and ranges. Thus:Pay
Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 152,000 USD - 241,500 USD for Level 3, and 184,000 USD - 287,500 USD for Level 4. You will also be eligible for equity and benefits.
But we already mentioned equity in Benefits; but it's okay to repeat? Might be duplication. Could keep equity only in Benefits and not repeat in Pay. However the original sentence includes equity and benefits together. To avoid duplication, we could keep Pay section only about salary ranges and determination, and Benefits about comprehensive benefits package and equity. That splits the sentence. That's acceptable as we are not inventing; we are splitting original info. Thus Benefits: "NVIDIA offers a comprehensive benefits package and eligibility for equity." Pay: "Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 152,000 USD - 241,500 USD for Level 3, and 184,000 USD - 287,500 USD for Level 4." Now check for any other substantive info: "Applications for this job will be accepted at least until August 31, 2026." Remove. Also "This posting is for an existing vacancy." Remove. Also "NVIDIA uses AI tools in its recruiting processes." That's maybe boilerplate? Could be considered info about recruiting process but not essential. Might be considered boilerplate? It's not EEO but it's about process. The instruction says remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. This line is not explicitly listed, but could be considered recruiting process info. Might be okay to keep? It's not about job duties. I'd lean to remove as it's not substantive about the role. However it's not explicitly