GPU Kernel Engineer: Build Fast AI Inference at Scale
Baseten
A leading AI acceleration company in San Francisco is seeking a GPU Kernel Engineer to optimize performance for machine learning models. You will be responsible for designing high-performance GPU kernels and using advanced techniques to boost computation efficiency. Ideal candidates have 1–5 years of CUDA development experience and a strong understanding of GPU architecture. This position offers competitive compensation, including equity, and comprehensive benefits including medical coverage and generous PTO. #J-18808-Ljbffr Baseten
Vacancy posted 15 hours ago
Similar jobs that could be interesting for youBased on the GPU Kernel Engineer: Build Fast AI Inference at Scale in San Francisco, CA vacancy
- ...the Team Our Inference team brings... ...state-of-the-art AI models, allowing... ...We’re hiring engineers to scale and optimize OpenAI... ...emerging GPU platforms. You’... ...from low-level kernel performance to... ...partner teams to build, integrate and... ...part of a small, fast-moving team building...SuggestedFull time
OpenAI
San Francisco, CA15 hours ago - ...seeking a talented software engineer to join their dynamic Inference team. This role involves... ...infrastructure for large-scale multimodal models, focusing... ...to push the boundaries of AI technology, ensuring reliable... .... If you thrive in fast-paced environments and enjoy...Suggested
- ...powers mission-critical inference for the world's most dynamic AI companies, like Cursor... .... Join us and help build the platform engineers turn to to ship AI products... ...We’re seeking a GPU Kernel Engineer to join our... .... You'll work in a fast-paced, intellectually...SuggestedFull timeFlexible hours
Baseten
San Francisco, CA15 hours ago - ...the Team We’re building high-performance... ...models at massive scale. As part of the inference team, you’ll be... ...GPUs by designing kernels, tuning memory layouts... ...a kernel-focused engineer to lead efforts... ..., and optimizing GPU kernels used in... ...OpenAI is an AI research and deployment...SuggestedFull time
OpenAI
San Francisco, CA15 hours ago - ...mission-critical inference for the world's most dynamic AI companies, like Cursor... ...Join us and help build the platform engineers turn to to ship AI... ...-modal workloads scale, the network is... ...engineers to lead our GPU Networking efforts... .... Optimize Kernels: You will work with...SuggestedFull timeFlexible hours
Baseten
San Francisco, CA15 hours ago $255k - $405k
...Lambda is the #1 GPU Cloud for ML/AI teams training... ...models, where engineers can easily,... ...and affordably build, test and... ...AI products at scale. Lambda’s product... ...clouds and managed inference services –... ...hardening, kernel integrity monitoring... ...Enjoy moving fast and making a...Full timeWork at officeLocal areaWork from homeFlexible hoursLambda
San Francisco, CA15 hours ago$315k
A leading AI research company in San Francisco is seeking a mid-senior GPU Performance Engineer. In this role, you'll architect systems that enhance GPU performance for groundbreaking AI models. Responsibilities include developing optimizations, collaborating with teams...$200k - $300k
...Labs: We build foundational... ...— unlocking AI's full potential... ...research to systems engineering to product... ...and serve as fast as the... ...world models at scale is a novel systems... ...— in kernels, in the serving... ...Optimize inference and serving end... ...Write and tune GPU kernels (CUDA...Full time- ...state-of-the-art AI models -... ...performance model inference and accelerating... ...optimization, and scaling of our... ...role, you’ll lead engineering efforts to ensure... ...performance at the kernel level, and... ...pipelines. Build tooling and observability... ...engineers on GPU performance,...Full time
OpenAI
San Francisco, CA15 hours ago - ...powers mission-critical inference for the world's most dynamic AI companies, like... .... Join us and help build the platform engineers turn to to ship AI... ...is building its own GPU infrastructure for large-scale inference. As we... ...RNIC issues, host kernel stalls, GPU driver...Full timeFlexible hours
Baseten
San Francisco, CA15 hours ago - ...mission-critical inference for the world's most dynamic AI companies, like Cursor... ...Join us and help build the platform engineers turn to to ship AI... ..., and improve GPU efficiency via profiling... .... Build large-scale, real-time... ...customization - enable fast evaluation, safe rollout...Full timeFlexible hours
Baseten
San Francisco, CA15 hours ago - ...the Team OpenAI’s Inference team powers the... .... We're a small, fast-moving team of engineers focused on delivering... ...of what AI can do. We’re... ...multimodal inference, building the infrastructure... ...multimodal models at scale. You’ll be part... ...including GPU utilization, tensor...Full time
OpenAI
San Francisco, CA15 hours ago - ...We're building the company which will de-risk... ...When people finance GPU clusters, the datacenters... ...for computer and inference, but sell to... ...Otherwise, as AI scales, compute only becomes... ...the same artifact, fast incremental feedback for every engineer, and a credible roadmap...Long term contractFull timeContract workFixed term contractWork at officeLocal areaRemote workVisa sponsorshipShift work
San Francisco Compute Company
San Francisco, CA15 hours ago $220k
Perplexity is looking for an engineer to join their team in San Francisco. You will work on building and operating the inference engine, supporting new models, migrating GPU kernels, and developing a Rust-based serving runtime. The ideal candidate has 3+ years of experience...$250k
...opportunities? Join a rapidly scaling AI cloud infrastructure provider building a next-generation GPU platform designed for AI training, experimentation, and inference at scale. The company is... ...Senior / Staff Site Reliability Engineer to support and scale large-scale...Full timeRemote workSan Francisco, CAmore than 2 months ago$190.9k - $232.8k
...a staff software engineer for GenAI inference, you will lead the... ..., and robust scaling. Your work will encompass... ...inference stack: kernels, runtimes,... ...guide standards to build and maintain instrumentation... ...with CUDA, GPU programming, and... ...is the data and AI company. More...Local areaWorldwide$190.9k - $232.8k
...staff software engineer for GenAI Performance and Kernel, you will own the... ...high-performance GPU kernels powering our GenAI inference stack. You will... ...performance at scale.What You Will DoLead... ...building high-performance... ...is the data and AI company. More than...Local areaWorldwide- ...Our mission is to scale intelligence to serve... ...who are building AI systems to power magical... ...work hard and move fast to do what’s best... ...team of researchers, engineers, designers, and... ...with Kubernetes, and GPU workloads on those... ...and throughput of inference. ~ Strong...Full timeWork experience placementWork at officeRemote workFlexible hours
Cohere
San Francisco, CA15 hours ago $300k
...GPU Optimisation Engineer — Real-Time Inference Want to push GPU performance to its... ...workloads? This team is building low-latency AI systems where... ...memory hierarchy, kernel launch overhead, occupancy... ..., profiling large-scale speech and... ...model ideas into fast, production-ready...RelocationVisa sponsorshipFree visatechire ai
San Francisco, CA5 days ago- ...worldwide.We’re a team of engineers, clinicians, and... ...PositionAs a Senior Systems GPU Engineer - AI & Robotics, you will... ...Development of Linux kernel internals, device... ...to real-time onboard inference—while serving as a... ...C++, Python, Bash) and building real-time, multi-...Local areaWorldwideFlexible hours
$100k - $120k
Coda Robotics is scaling the compute infrastructure that powers... ...models. As training and inference workloads grow, we need kernel‑level innovations to... ...team of kernel and system engineers focused on performance-critical... ...for CPU (AVX/ARM NEON), GPU (CUDA/ROCm), and hardware...$185k
About the RoleThe Engineering Acceleration team builds and operates the foundational systems... ...integration systems for a fast-growing engineering organization... ...bottlenecks.Use modern AI tools to rethink CI failure... ...or operated CI systems at scale, especially in environments...Work at officeLocal areaRemote workFlexible hours- ...COMPANY We're building autonomous... ...operate the inference systems that... ...This is an engineering role, not a research... ...their work fast and reliable... ...quantization, custom kernels, scheduling... ...grade, large‑scale serving... ...Experience with GPU‑accelerated... ...#J-18808-Ljbffr MakerMaker.AI
- Mirai Labs in San Francisco seeks engineers to join a senior team building the full on-device stack for real-... ...You will primarily work on uzu, our inference engine, and focus on supporting... ...experience in writing high-performance GPU kernels or Rust systems programming. We...Local area
$250k - $300k
...vertically integrated AI infrastructure... ...a team that is building the future,... ...believe in the scale of our ambition... ...owning the inference stack end to end... ...with customer engineering teams to tailor... ...SGLang to the CUDA kernels underneath,... ...of concept, run fast experiments to...Temporary work$206.3k - $388k
...for a Principal ML Engineer to architect and scale the multimodal data... ...engineering and applied ML building distributed, GPU-accelerated systems... ...determine how fast and how well Adobe... ...data Scale up inference throughput across the... ...impact, powered by AI and driven by human...Full timeTemporary workLocal areaWorldwide$342k
...demands of advanced AI workloads. The... ...for building the next generation... ...the RoleAs an Engineer on our hardware... ...work with our kernel, compiler and machine... ...training and inference on our models.... ...drive decisions on scale up, scale out,... ...of GPU and/or other AI...Work at officeLocal areaRelocation packageFlexible hours- ...Developer Productivity engineer to support OpenAI’s Inference Runtime teams. These... ...Engineer to help scale the engineering systems... ...work. The systems you build directly impact OpenAI... ...instability, GPU scheduling, or test environment... ...OpenAI is an AI research and deployment...Full time
OpenAI
San Francisco, CA15 hours ago $320k
...interpretable, and steerable AI systems. We want AI... ...researchers, engineers, policy experts,... ...together to build beneficial AI systems... ...mandate is to make inference deployment boring and... ...deployment systems at scale and gravitate... ...production across GPU, TPU, and Trainium...Full timeWork at officeVisa sponsorshipFlexible hoursShift workAnthropic
San Francisco, CA15 hours ago- ...About the Team The scaling team team builds foundational components... ...Role As a software engineer on the Scaling team, you... ..., building custom kernels, contributing to compiler... ...excited to work in a fast-paced, highly collaborative... ...OpenAI is an AI research and deployment...Full timeWork at officeLocal areaRelocation package3 days per week
OpenAI
San Francisco, CA15 hours ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to GPU Kernel Engineer: Build Fast AI Inference at Scale. Be the first to apply!
