Senior GPU Kernel Engineer: Inference Throughput
CoreWeave
CoreWeave is seeking a Senior Engineer for its Benchmarking & Performance team to own kernel authoring and optimization for LLM inference. You will write and tune CUDA kernels, optimize tensor cores, and push end-to-end latency down while maintaining accuracy.
You will lead benchmarking workflows (MLPerf), mentor engineers, and collaborate with cross-functional partners. Experience with CUDA, C++, Python, and GPU architectures is required; familiarity with vLLM, TensorRT-LLM, llm-d, SGLang is a
#J-18808-LjbffrVacancy posted 3 hours ago
Similar jobs that could be interesting for youBased on the Senior GPU Kernel Engineer: Inference Throughput in Bellevue, WA vacancy
$184k - $287.5k
We're now looking for a Sr. Inference Engineer, for GPU Kernel Optimization! What does it take to push every LLM inference operation to its performance... ...of how kernel selection drives model-level throughput and latency.Working knowledge of GPU kernel optimization...SeniorFull time- ...NVIDIA in Seattle, WA seeks outstanding AI systems engineers to advance the inference software stack for AI workloads. You will develop libraries, code generators, and GPU kernel technologies for NVIDIA hardware, including new abstractions and runtimes for large language...Senior
NVIDIA
Seattle, WA4 hours ago $182k - $242k
...for high-performance GPU infrastructure... ...rendering, and real-time inference. Our stack is engineered for speed, scale, and... ...We're looking for a Senior Engineer for... ...Performance team, focused on kernel authoring and... ...serving—squeezing maximum throughput and minimum latency...SeniorPermanent employmentFull timeTemporary workCasual workWork at officeFlexible hoursCoreWeave
Bellevue, WA23 days ago- ...NVIDIA is seeking a Senior Software Engineer for Quantized Inference to accelerate the development of efficient inference... ...and sparse recipes, work on kernel and model-level implementations,... ...collaborate with partner teams to optimize throughput and interactivity across Megatron...Senior
NVIDIA AI
Redmond, WA4 hours ago $165k - $242k
...CoreWeave in Bellevue, WA is seeking an experienced engineer to lead design reviews and optimize distributed systems. The role requires 5-8 years in cloud services, strong skills in Python or Go, and hands-on experience with Kubernetes. Key responsibilities include defining...SeniorFlexible hoursCoreWeave
Bellevue, WA11 hours ago$152k - $241.5k
...lasting impact on the world.NVIDIA is hiring a Senior Compiler Engineer to join our team driving the next generation of GPU systems programming. We are redefining how... ...developers to write memory-safe, high-performance GPU kernels in idiomatic Rust.What you’ll be doing:Develop...SeniorFull timeRemote work$139k - $204k
...What You’ll Do Senior engineers are area owners who lead... ...improvements to latency, throughput, and reliability... ...our Kubernetes‑native inference platform and meet strict... ...‑per‑token analytics, GPU resource isolation).... ...Experience with CUDA kernels, NCCL/SHARP, RDMA/NUMA...SeniorPermanent employmentTemporary workCasual workWork at officeRemote workFlexible hoursShift workCoreWeave
Bellevue, WA4 hours ago$226k - $307k
...and System Optimization Engineer, you will orchestrate... ...for more efficient inference by sharing various parts... ...models, write custom CUDA kernels, and build highly... ...system resources (CPU/GPU/interconnect) to various... ...low latency or high throughput.Deep expertise in working...SeniorFull timeTemporary workRelocation package$224k - $356.5k
.... An era in which our GPU acts as the brains of... ...leading open-source LLM inference frameworks — identify... ...FLOP/s, interconnect throughput) to observed inference... ...Computer Science, Computer Engineering, Electrical... ...on experience with GPU kernel development or optimization...SeniorFull timeLocal area- ...NVIDIA is seeking a seasoned engineer to advance LLM inference on edge AI hardware. You’ll evaluate frameworks, map model architectures to GPU, and optimize across multi-node deployments, focusing on performance and stability. You’ll own validation workflows, develop...Senior
NVIDIA AI
Seattle, WA4 hours ago - ...NVIDIA Gruppe is seeking a Senior Software Engineer for Quantized Inference in Redmond, Washington. You will be responsible for implementing quantized and sparse recipes in inference engines and enhancing developer productivity across the team. Successful candidates...Senior
NVIDIA Gruppe
Redmond, WA4 hours ago $184k - $287.5k
NVIDIA's invention of the GPU 1999 sparked the growth of... ...company”.We're looking for a Senior Performance Compiler Engineer to join our team and work... ...both training and inference. You will be immersed in a... ...MLIR to optimize high-level kernel descriptions (written in Triton...SeniorFull timeRemote work$152k - $241.5k
...computing. An era in which our GPU acts as the brains of... ...for a Deep Learning Compiler Engineer. NVIDIA is hiring software engineers... ...has been the backbone of NVIDIA inference engine, spanning across data centers... ..., such as PyTorch.GPU kernel generation with high performance...SeniorFull timeRemote work$152k - $241.5k
We are now looking for a Senior Software Engineer for Quantized Inference! NVIDIA is seeking software engineers to... ...sparsified variants — unlocking throughput and latency gains without regressing... ...new recipe demands corresponding kernel and model-level implementations...SeniorFull time$152k - $241.5k
...developing and optimizing math kernels to extract the highest... ...architectures.Optimize kernels for peak throughput on both silicon and software... ...across NVIDIA including the GPU architecture, NVVM/PTX... ...in Computer Science, Computer Engineering, or related field (or equivalent...SeniorFull time$100k - $150k
...GPU Systems Engineer - Remote Bright Vision Technologies is a technology... ...GPU platforms for AI training, inference, scientific computing, and high-throughput data processing workloads. The... ...implement high-performance CUDA kernels for compute-intensive workloads...Full timeH1bLocal areaImmediate startRemote workVisa sponsorship$217k - $307k
...that runs on it to achieve maximum throughput at the most optimal power levels. The... ...meet the required specifications. As a GPU performance software engineer within the Software Performance team... ...experience debugging/optimizing GPU kernels using tools like Nsight.Strong...SeniorFull timeTemporary workRelocation package$184k - $287.5k
NVIDIA is seeking an NCX Senior Engineer to join our DSX team, collaborating closely with strategic... ..., including distributed training, inference optimization, and MLOps pipelines constructed... ...using Kubernetes, containers, and GPU scheduling systems aligned to NCP builds...SeniorFull timeRemote work$182k - $242k
...more at What You'll Do: The Systems Engineering team owns the Linux kernel and host software stack underneath one of the largest GPU fleets in the world. When something... ...upstream the fix. About the role: As a Senior Software Engineer on the Systems Engineering...SeniorPermanent employmentFull timeTemporary workCasual workWork at officeFlexible hoursCoreWeave
Bellevue, WA18 days ago- ...A technology leader in computing solutions is seeking a Senior Software Engineer to work on system software for data center products. The role involves deep technical expertise in firmware and kernel development, along with customer-facing responsibilities. Ideal candidates...Senior
NVIDIA
Redmond, WA4 hours ago $152k - $241.5k
NVIDIA's invention of the GPU 1999 sparked the growth of the PC gaming market, redefined... ...”.We are looking for versatile software engineers for our XLA team. NVIDIA is at the center... ...learning workloads. You will optimize inference and training performance for the JAX framework...SeniorFull timeRemote work$182k - $242k
...that measure latency, throughput, jitter, and cost-per-... ...end MLPerf Training and Inference runs, including... ...the team. Break down engineering tasks into clear milestones... ...performance-critical GPU systems (CUDA, NCCL,... ...Background working with CUDA kernels, NCCL/SHARP, RDMA/NUMA...SeniorPermanent employmentTemporary workCasual workWork at officeRemote workFlexible hoursCoreWeave
Bellevue, WA3 hours ago- ...a Model Optimization & Deployment Engineer, you will focus on bringing highly... ...optimize the ML models, write custom CUDA kernels, and build highly concurrent inference code to ensure real-time,... ...runtime efficiency optimization for GPU clusters. Experience with end-to...SeniorTemporary workRelocation package
Zoox
Seattle, WAmore than 2 months ago $184k - $287.5k
...development. The role of a Deep Learning Systems Engineer would be to analyze the performance and... ...? In this role you will find how CPU, GPU, networking, and IO relate to deep... ...Operating Systems (Linux), Compilers, GPU kernels (CUDA), DL Frameworks (PyTorch, TensorFlow...SeniorFull time$153k - $204k
...What You'll Do: The Systems Engineering team owns the host software... ...Kubernetes worker — the OS image, kernel and drivers, and the hardware... ...it reaches one of the largest GPU fleets in the world, and we're... .... About the role: As a Senior Software Engineer on the Systems...SeniorPermanent employmentFull timeTemporary workCasual workLive inWork at officeFlexible hoursCoreWeave
Bellevue, WA18 days ago$184k - $287.5k
...secure for millions globally. We seek a Senior Engineer to lead technical efforts in deploying advanced... ...PCs. By combining powerful local inference (Nemotron models) with strong privacy routers... ...pipelines (Ollama, Llama.cpp, vLLM), GPU-accelerated computing (CUDA, TensorRT),...SeniorFull timeLocal areaShift work$200k - $275k
...their identity, platform, and security engineering teams, write production code in their environment... ...their engineers on the patterns.Engage senior leadership. Brief the CISO, CIO,... ...that authenticate and authorize at high throughput.Ability to travel, 35% (on occasion internationally...SeniorLocal areaWorldwideFlexible hoursShift work$188k - $275k
...more at What You'll Do: The Field Engineering organization at CoreWeave is dedicated... ...reliable compute that customers can train and inference on at scale, spanning infrastructure... ...entire customer lifecycle: leading new GPU cluster bring-up and acceptance, driving...SeniorPermanent employmentFull timeContract workTemporary workCasual workWork at officeFlexible hoursCoreWeave
Bellevue, WA23 days ago$207k - $275k
...mission-critical. We're seeking a Senior Manager of Production Engineering to lead and expand our SRE team and... ...operational visibility. Familiarity with GPU-accelerated workloads, including... ...supporting training or inference at scale. Background in compliance...SeniorPermanent employmentFull timeTemporary workCasual workWork at officeFlexible hoursCoreWeave
Bellevue, WA23 days ago$152k - $241.5k
...AI workloads, and we are looking for an engineer focused on performance validation, analysis... ...intersection of deep learning compilers, GPU systems, and automation infrastructure,... ...benchmarking systems to measure latency, throughput, and efficiency of AI and HPC workloadsAnalyze...SeniorFull timeRemote work
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Senior GPU Kernel Engineer: Inference Throughput. Be the first to apply!
Related searches
- senior lead project manager Bellevue, WA
- senior robotics software engineer Bellevue, WA
- senior devops engineer remote Bellevue, WA
- senior sas administrator Bellevue, WA
- senior IT manager Bellevue, WA
- sr project manager Bellevue, WA
- senior windows systems engineer Bellevue, WA
- consultant senior consultant Bellevue, WA
- senior manager data science Bellevue, WA
- senior ui ux designer Bellevue, WA