Deep Learning Software Engineer, FlashInfer - New College Grad 2025
We are now looking for a Deep Learning Software Engineer, FlashInfer. 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. Today, we’re tapping into the unlimited potential of AI to define the next era of computing. An era in which our GPU acts as the brains of computers, robots, and self-driving cars that can understand the world. Doing what’s never been done before takes vision, innovation, and the world’s best talent. As an NVIDIAN, you’ll be immersed in a diverse, supportive environment where everyone is inspired to do their best work. Come join the team and see how you can make a lasting impact on the world.
We're looking for outstanding AI systems engineers to develop groundbreaking technologies in the inference systems software stack! We build innovative AI systems software to accelerate for AI inference. As a member of the team, you'll develop libraries, code generators, and GPU kernel technologies for NVIDIA's hardware architecture. This means designing and building things like new abstractions, efficient attention kernel implementations, new LLM inference runtimes components, and kernel code generators to accelerate large language models, agents, and other high-impact AI workloads.
What you'll be doing:
Innovating and developing new AI systems technologies for efficient inference
Designing, implementing, and optimizing kernels for high impact AI workloads
Designing and implementing extensible abstractions for LLM serving engines
Building efficient just-in-time domain specific compilers and runtimes
Collaborating closely with other engineers at NVIDIA across deep learning frameworks, libraries, kernels, and GPU arch teams
Contributing to open source communities like FlashInfer, vLLM, and SGLang
What we need to see:
Bachelor's degree in Computer Science, Electrical Engineering, or related field (or equivalent experience); PhD are preferred
Strong experience in developing or using deep learning frameworks (e.g. PyTorch, JAX, TensorFlow, ONNX, etc) and ideally inference engines and runtimes such as vLLM, SGLang, and MLC.
Strong Python and C/C++ programming skills
Ways to stand out from the crowd:
Background in domain specific compiler and library solutions for LLM inference and training (e.g. FlashInfer, Flash Attention)
Expertise in inference engines like vLLM and SGLang
Expertise in machine learning compilers (e.g. Apache TVM, MLIR)
Strong experience in GPU kernel development and performance optimizations (especially using CUDA C/C++, cuTile, Triton, or similar)
Open source project ownership or contributions
You will also be eligible for equity and benefits.
Average salary estimate
If an employer mentions a salary or salary range on their job, we display it as an "Employer Estimate". If a job has no salary data, Rise displays an estimate if available.
Lead cross-disciplinary efforts to build and operationalize low-resource language LLMs and language-based AI products that prioritize linguistic inclusion and responsible AI at NVIDIA.
Lead the design, training, and production deployment of LLM/VLM-powered prediction and planning systems for production autonomous vehicles at NVIDIA's Santa Clara team.
Pacific Fusion seeks a DevOps Engineer to own CI/CD, build systems, and developer tooling to accelerate delivery of physics and controls software at our Livermore site.
Experienced Android developer needed to own feature development and deliver scalable, accessible apps using Kotlin and Jetpack Compose in a 100% remote, 12-month contract role.
Western Alliance Bank is hiring a Staff Engineer II — Full Stack .NET developer to lead design and delivery of secure, scalable Azure-based services and APIs while mentoring teams and driving DevOps practices.
Partnerize is hiring an experienced Site Reliability Engineer to improve platform reliability, automate infrastructure, and support large distributed applications in a remote role based in Orlando, FL.
Sysco is hiring an experienced SAP Software Engineer to lead ABAP development and SAP integration initiatives for its Woodridge operations in a hybrid work model.
Senior Developer for Power Generation IT/OT to build and support web and desktop applications, troubleshoot production issues, and coordinate vendor support in a rotating on-call environment.
First American Trust is hiring a remote Software Engineer in California to build and maintain Azure-friendly, cloud-native applications using Python and full-stack technologies.
DXC Technology seeks a seasoned LifeComm Product Developer/SME with 10+ years of LifeComm experience and strong mainframe assembler skills to support US life insurance clients in Jacksonville, FL.
Mercor seeks experienced software engineers to author realistic, test-backed multilingual bug-fix tasks drawn from real GitHub issues to support AI evaluation and training.
Autodesk is hiring a Senior Software Engineer to build and scale Spring Boot microservices, ETL pipelines and data-driven financial applications on AWS for its Digital Business Platforms team.
Senior Lead Platform Engineer to help design, build, and scale Coupa’s cloud-native SaaS platform services using Ruby and Go for a global spend-management product.
VALIS is hiring a mid-to-senior full-stack engineer to build and own customer-focused features for an early-stage B2B SaaS platform advancing metals recycling.
Lead engineering strategy and execution for Fandango's portfolio, building API-first, cloud-native and AI-enabled platforms that scale for millions of users and partners.
NVIDIA is a publicly traded, multinational technology company headquartered in Santa Clara, California. NVIDIA's invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined computer graphics, and ignited the era of modern AI.
87 jobs
🔮
Hi, I'm Risa! Your AI Career Copilot
you, just ask me below!
