SGLang Jobs

Our LLM Inference Performance Analysis and Optimization team is seeking a Senior Inference Engineer specializing in GPU Kernel Optimization. This role is crucial for maximizing the performance of LLM inference operations by developing advanced infrastructure and tooling. You will build silicon-measured kernel benchmarking systems, model-level performance projection tools, and agentic optimization systems that enhance GPU kernels at the assembly layer. The position involves close collaboration with compiler, kernel, hardware, and framework teams across NVIDIA to identify and address performance bottlenecks, driving measurable improvements in LLM inference.

$184k - $288k

NVIDIA is seeking a Senior System Software Engineer to join its GPU-accelerated deep learning software team, focusing on the Dynamo platform. This role involves developing open-source software for efficient Generative AI inference on GPUs, making AI model design and deployment more accessible. The team is building a fast-paced inference platform to support the growing AI revolution, enabling breakthroughs across various domains like image classification, speech recognition, and natural language processing.

$224k - $431k

At NVIDIA OpenShell, we are building the runtime infrastructure for secure, scalable, production-grade AI agents. As an OpenShell Research Engineer, you will help bring the latest advances in agentic systems into the runtime, tools, and workflows that enterprise builders rely on. This role sits at the intersection of research, product, and engineering, requiring you to identify promising methods from academia and industry, validate their impact through prototypes and benchmarks, and help integrate the best ideas into the product.

$184k - $288k

NVIDIA's CUTLASS is a popular open-source ecosystem for high-performance linear algebra and Tensor Core primitives, providing C++ and Python abstractions for computations on NVIDIA GPUs. This role focuses on bridging the gap between current and theoretical performance, optimizing GPU kernels and fusion opportunities within deep learning models. You will develop tooling for automated benchmarking and analysis, becoming an authoritative resource on kernel performance and collaborating with various NVIDIA teams.

$152k - $288k

An applied research team within NVIDIA's Networking Systems & Software Architecture group is tackling complex AI infrastructure challenges. The team develops systems-level software to optimize data movement between GPUs, nodes, and storage at the speed required for modern AI, focusing on low-level transport, hardware-software co-design, and communication frameworks integrated into AI stacks. Their work also extends to emerging areas like quantum computing interconnects. This Principal Architect role will define the research agenda and architectural direction for NVIDIA's large-scale AI systems communication, encompassing GPUs, DPUs, NICs, and heterogeneous storage. The position demands the ability to define project scope, conduct original research, publish findings, and translate breakthroughs into production-ready software for industry-wide deployment.

$272k - $431k

NVIDIA is seeking a Deep Learning Communication Architect to join its software architecture group. This role involves scaling Deep Neural Network (DNN) models and training/inference frameworks to systems with hundreds of thousands of nodes. You will be instrumental in optimizing communication performance by identifying and eliminating bottlenecks in data transfer and synchronization. The position requires designing efficient communication protocols tailored for deep learning workloads and collaborating with hardware and software teams to craft systems that leverage high-speed interconnects and communication libraries. You will also research and evaluate new communication technologies to enhance performance and scalability, and develop proofs-of-concept to validate new strategies.

$184k - $357k

NVIDIA is seeking a motivated Deep Learning engineer to integrate advanced CUDA features and Distributed Runtime technologies into AI stacks, including frameworks like PyTorch, TRT-LLM, vLLM, SGLang, and JAX. You will join the team responsible for core CUDA features and runtimes that scale Deep Learning and HPC applications, addressing diverse multi-GPU demands from large-scale training to low-latency inference. Your work will enhance the productivity and performance of AI applications, accelerating community adoption through AI toolkits. This role offers a significant opportunity to advance the state of the art in AI technologies.

$184k - $357k

NVIDIA is seeking a Senior Software Engineer to specialize in Deep Learning Inference. This role involves designing, building, and optimizing GPU-accelerated software for AI applications, focusing on high-performance deep learning frameworks like SGLang and vLLM for efficient large-scale model serving and inference. You will contribute to improving these platforms, enabling the smooth deployment of advanced language models and working with the deep learning community to implement and release the latest algorithms. The work will concentrate on enhancing the performance of state-of-the-art LLM and Generative AI models across various NVIDIA accelerators, utilizing open-source tools and kernels for optimization.

$184k - $357k

NVIDIA is seeking a motivated Deep Learning engineer to integrate advanced communication technologies into AI stacks, including PyTorch, TRT-LLM, vLLM, and SGLang. You will work with the team that created communication libraries like NCCL and NVSHMEM, and technology like GPUDirect, to scale Deep Learning and HPC applications. Your work will directly impact AI application performance by improving communication between GPUs, making AI toolkits easier for the community to use. This role offers an outstanding opportunity for someone with an AI background to advance the state of the art in this space.

$184k - $357k

SpaceXSI is building the high-performance inference platform that serves Grok to millions of users daily with exceptional speed and reliability. As a Member of Technical Staff - Inference, you will be instrumental in designing and optimizing large-scale model serving systems from the ground up. This includes owning distributed infrastructure components like global KV cache, continuous batching, load balancing, and auto-scaling, as well as delving into deep low-level optimizations such as GPU kernels, quantization, and speculative decoding. This is a high-impact role where your contributions will directly influence the speed and reliability of user interactions with Grok at a massive scale.

$180k - $440k

NVIDIA is seeking a dedicated Software Engineer, ML Performance to join our team in Santa Clara, CA. In this role, you will engage directly with the latest AI technologies and work on optimizing performance at an outstanding scale. Your expertise will ensure that our groundbreaking solutions operate flawlessly and continue to lead the industry. You will be immersed in an inclusive, 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.

$224k - $357k

NVIDIA is seeking a Senior Validation Engineer to join the DGX Server Product Engineering Team. In this role, you will collaborate with a team of hardware and software engineers to develop and implement sophisticated automated test plans for our leading GPU-accelerated computing products. You will be instrumental in ensuring the performance and reliability of cutting-edge AI hardware by developing and tuning workloads, adapting state-of-the-art AI training and inference frameworks, and applying architectural analysis to characterize workload behavior and identify bottlenecks. This position offers the opportunity to make a significant impact on the future of computing by working on AI-driven technologies.

$136k - $259k

Nebius is building a full-stack AI cloud platform for the global AI economy, supporting developers and enterprises from data and model training through to production deployment. As a Forward Deployed Engineer, you will work alongside Physical AI customers to understand their workloads and production requirements, translating these into actionable insights for our core infrastructure products. You will also investigate and prototype new product opportunities based on unmet customer needs, helping to shape the future of Nebius' offerings. This hands-on role involves writing code, deploying and benchmarking models, building agents, and troubleshooting infrastructure in close collaboration with customers, NVIDIA, Product, and Engineering teams.

Nebius is building a full-stack AI cloud platform to support developers and enterprises from data and model training through to production deployment. As a Senior Machine Learning Engineer on the Applied AI team, you will own model and endpoint optimization from model artifacts through production deployment. Your work will span model internals, quantization, model compression, speculative decoding, KV-cache optimization, inference engines, and serving architecture to improve latency, throughput, memory efficiency, GPU utilization, and cost per token while preserving model quality and reliability. You will collaborate with kernel and platform engineers to investigate serving problems, compare configurations, and resolve performance and quality regressions, validating improvements through reproducible benchmarks and safe production rollouts.

$195k - $262k

Nebius is building a full-stack AI cloud platform for the global AI economy, supporting developers and enterprises from data and model training through to production deployment. As a Forward Deployed Engineer, you will work directly with Physical AI customers to understand their workloads and production requirements. Your insights will shape our core infrastructure products and inform future development by connecting needs across Physical AI industries with product decisions. You will also investigate opportunities for new Nebius products by developing hypotheses about unmet needs, examining demand, and building prototypes to test with customers. This hands-on role involves writing code, deploying and benchmarking models, building agents, and troubleshooting infrastructure alongside customer engineers, with close collaboration across customers, NVIDIA, Product, and Engineering.

$180k - $224k

SambaNova is seeking a Senior Software Engineer to join the ML Infrastructure team. This role is central to our mission as an inference-first company, focusing on designing, building, and operating the production-grade inference infrastructure that powers SambaNova's serving stack on our Reconfigurable Dataflow Unit (RDU) architecture. You will transform state-of-the-art inference techniques into reliable, high-throughput, low-latency services exposed to customers through SambaStack and SambaCloud. This position involves end-to-end ownership of systems including request scheduling, advanced decoding algorithms, caching layers, API surfaces, and accuracy infrastructure, and requires close collaboration with ML, compiler, runtime, and product teams.

$200k - $275k

As a new grad AI Performance Engineer, you will be responsible for bringing up new open-source foundation models on the SambaNova dataflow platform and optimizing their performance. This involves profiling model execution, identifying performance bottlenecks across compiler, runtime, and hardware layers, and applying optimizations such as quantization, kernel fusion, and improved scheduling. You will collaborate with machine learning, compiler, runtime, and hardware teams to integrate performance improvements into SambaNova products and benchmark throughput and latency to track changes across releases.

$131k - $197k

Together AI

The Speculative Decoding team at Together AI focuses on developing draft models and algorithms to accelerate large language model generation without altering outputs. Their work integrates model training, inference algorithms, and serving systems, optimizing all three for reduced cost and latency. As a research intern, you will explore open questions in speculative decoding, including new drafter architectures, verification schemes, knowledge distillation, and adaptive drafters. You will train and fine-tune draft models at scale on GPU clusters and evaluate your solutions against realistic serving workloads, such as long-context and agentic traffic.

d-Matrix is seeking a Senior Staff Inference Performance Engineer to join their Inference Cloud Engineering team. This role is responsible for the end-to-end performance of workloads deployed on d-Matrix's inference services, ensuring they perform at least as well as on bare metal. The engineer will diagnose and isolate performance issues across the full serving path, from orchestration to inference internals, and will be responsible for either fixing problems directly or handing them off to the appropriate owning team with clear evidence. The role involves assessing scalability, defining node requirements for optimal deployment, and building telemetry and benchmarks to support these efforts. The ideal candidate will mentor other engineers in a profiling-first methodology.

$175k - $265k

NVIDIA Cloud Functions is seeking a motivated AI/ML Engineer with expertise in AI platform engineering at scale. The team develops and manages a serverless deployment platform designed to enable and scale AI inferencing workloads. This platform utilizes globally distributed orchestration of workloads on Kubernetes clusters backed by GPUs, operating in a cloud-agnostic manner. The role involves working with a team of innovative engineers to deliver a top-tier product for both external clients and internal NVIDIA teams, contributing to the forefront of cloud engineering paradigms for AI at scale.

$152k - $288k