GPU Kernel Engineer for High-Performance AI Inference
Baseten
Baseten is seeking a GPU Kernel Engineer in New York, NY. The ideal candidate will design high-performance GPU kernels and optimize computation for AI workloads. Responsibilities include implementing advanced features, contributing to open-source GPU libraries, and collaborating with research teams. The position offers competitive compensation, 100% coverage of insurance, and flexible PTO. Join Baseten to be part of cutting-edge AI acceleration efforts. #J-18808-Ljbffr Baseten
- Character.ai in Menlo Park is seeking a seasoned Research Engineer specializing in GPU computing. You will be responsible for designing high-performance kernels for our training and inference workloads using CUDA/CUTLASS, C++, and Python. The ideal candidate has strong...Performance3 days per week
- ...Senior GPU Systems / AI Infrastructure Engineer (NYC) Location: New York City... ...(Series A-C / high-growth AI infra)... ...model training and inference. This role sits at... ...intersection of GPU systems, kernel optimisation,... ...compute, and high-performance AI workloads ....PerformancePermanent employment
$180k - $360k
...powers mission‑critical inference for the world's most dynamic AI companies, like Cursor,... ...Role We’re seeking a GPU Kernel Engineer to join our team at the... ...Inference Stack Driving model performance optimization... ...Responsibilities Design and implement high‑performance GPU kernels...PerformanceFlexible hours- ...trading firm hiring a Senior HPC Engineer to help build and scale large-scale HPC and GPU infrastructure supporting AI, machine learning and... ...designing, building and operating high-throughput compute... ...infrastructure specialists to improve performance, scalability and...Performance
- ...professional in New York to design and operate large-scale GPU infrastructure for model inference and reinforcement learning. The role demands several... ...experience in deploying GPU systems, optimizing model performance, and working with frameworks like SGLang and Megatron....Performance
$350k
...and steerable AI systems. We want... ...committed researchers, engineers, policy experts... ...Anthropic's inference fleet serves... ...: accelerator kernels, model servers,... ...it to a high bar across four... ...how the fleet performs against its theoretical... ...with GPU/TPU/accelerator...PerformanceVisa sponsorship$320k
Anthropic is hiring a Staff + Senior Software Engineer, specializing in Inference, to design and build distributed systems for its AI platform, Claude. This position... ...infrastructure, distributed systems, and optimizing performance in a high-scale environment. The role requires a...Performance$160k - $200k
...powers mission-critical inference for the world's most dynamic AI companies, like... ...build the platform engineers turn to to ship AI... ...the intersection of high-performance computing (HPC) and... ...tools that measure GPU FLOPS, stress-test... ...disaggregated serving, and kernel-level optimizations...PerformanceFlexible hours$174k - $253k
Google is searching for experienced Software Engineers to develop optimizations for the latest... ...experience, alongside expertise in modern GPU architectures and low-level GPU programming. This role involves addressing performance bottlenecks and influencing GPU software direction...Performance$315k
...interpretable, and steerable AI systems. We want... ...researchers, engineers, policy experts,... ...innovations in GPU performance and systems engineering... ...improve inference efficiency. Working... ...techniques from custom kernel development to... ...hardware interfaces to high-level ML...PerformanceWork at officeVisa sponsorshipFlexible hours$224k - $356.5k
...unlimited potential of AI to define the next era... ...computing. An era in which our GPU acts as the brains of... ...now looking for a GPU Performance Engineer for Neural... ...execution. Translate high-impact Python, NumPy, or... ...overhead, memory pressure, kernel launch overhead, and framework...Performance- ...Intelligence Hardware Engineer About the job Artificial... ...and coming innovative AI start-up is seeking a highly skilled and innovative... ...optimization. Conduct performance analysis and... ...and technologies (e.g., GPU, FPGA, ASIC) for AI inference and training. Familiarity...PerformanceRemote workVisa sponsorship
- Obsidian is seeking an MLOps Engineer to join their AI lab's cutting-edge GenAI team in New York. This... ...advanced AI models using PyTorch and kernel-level programming. The ideal candidate... ...infrastructure, with skills in custom GPU kernel optimization. This position offers...Full time
- ...Founder Vice President, AI Inference Software About the Company... ...in shaping the future of high-performance AI inference. The... ...building and mentoring an elite engineering team, and partnering with... ...skills in areas such as GPU programming, kernel optimization, and runtime...Performance
$180k - $270k
...infrastructure company in New York is seeking an Electrical Engineer to design and develop systems for high-density GPU data centers. Candidates should have a Bachelor’s... ...teams to validate electrical system performance. The salary range for this position is $180,000 -...Performance- Reflection AI is seeking an engineer to design, build, and operate large-scale GPU infrastructure for high-throughput model inference and mid-training workloads. You will... ..., tackling kernel-level optimizations and low-level performance issues across GPU and networking...Performance
$109k - $163.7k
...seeking a skilled LLM Engineer I to join our team... ...that ensure all AI systems,... ...validated for compliance, performance, and patient safety... ...AutoGen, Semantic Kernel) including tool/... ...deployment, including inference optimization,... ...communities by delivering high-quality care to...PerformanceTraineeshipLocal areaFlexible hours$152k - $287.5k
NVIDIA is seeking a Senior Developer Technology Engineer for High-Performance Databases in New York. This role involves researching and developing techniques to GPU-accelerate databases and ETL applications, collaborating with industry experts, and optimizing complex workloads...Performance- About Us: AI needs a new infrastructure... ...for instant GPU access, sub-... ...serve low-latency inference, fine-tune... ...and experienced engineering and product leaders... ...lead to pick high-impact bets and... ...inference performance our work on Flash Attention 4 kernels Work with engineering...PerformanceWork at office
- ...technology company is looking for exceptional generalist engineers who thrive with autonomy. This fully remote role allows you to work on high-impact projects across the vLLM stack, from optimizing CUDA kernels to designing distributed orchestration systems. Ideal candidates...Remote job
$124.9k - $228.9k
You’ll join a software engineering team building internal AI solutions that support teams... ...LlamaIndex, and Semantic Kernel. Develop Retrieval-Augmented... ...business value. Deliver high-impact features by collaborating... ...goals. Drive quality and performance through automated testing,...PerformanceTemporary workLocal area$180k - $360k
A leading AI platform provider in New York seeks a Model API Engineer focused on infrastructure for hosted AI models. Responsibilities include optimizing performance, building benchmarking frameworks, and collaborating on robust model serving solutions. Ideal candidates...Performance$106.9k - $176.5k
.... Forward Deployed Engineer – Applied AI - Senior - Financial Services... ...teams to deliver high-value AI capabilities. Improve performance, resilience,... ...AutoGen, CrewAI, Semantic Kernel, NVIDIA NIM etc.) Ability... ....) Familiarity with inference optimization...PerformanceSummer holidayFlexible hours- NVIDIA is currently seeking a Senior Developer Technology Engineer for High-Performance Databases! Would you enjoy researching new algorithms and memory... ...What You Will Be Doing Research and develop techniques to GPU-accelerate high performance database and ETL applications....Performance
$165k - $242k
...CoreWeave is the AI Hyperscaler™, delivering a cloud... ...AI labs with the most performant, efficient and resilient... ...CoreWeave is seeking a highly skilled and motivated Systems Kernel Engineer to join our HAVOCK Team... ...storage, virtualization, GPU/DPU enablement). Stack...PerformancePermanent employmentTemporary workCasual workWork at officeRemote workFlexible hours- Sweep is seeking an exceptional ML engineer to stabilize and scale our... ...humanity’s defense layer for the AI age, with a bias toward performance under pressure in high-stakes settings. You’ll join a... ...ML/LLM pipelines, and own the inference loop from sensing to decision....Performance
$280k
...and steerable AI systems. We want... ...researchers, engineers, policy experts... ...problems. As a Performance Engineer, you'll... ...WITH: * High performance, large... ...ML systems * GPU/Accelerator programming... ...Implement GPU kernels to adapt our... ...low-precision inference * Write a...PerformanceFull timeWork at officeVisa sponsorshipFlexible hours- ...foundation for AI teams. With instant GPU access, sub-second... ...low-latency inference. We have thousands... ...and experienced engineering and product leaders... ...lead a group of highly experienced... ...data handling, and performance optimization. Who... ...(Linux kernel, file systems, containers...Performance
- ...Data Center Mechanical Engineer who can help Jane Street... ...for the most demanding AI workloads. While we won... ...practice - between our high-level thinking around... ...while maintaining the performance standards needed for our... ...center infrastructure and GPU/HPC systems to support...PerformanceWork at office
$70 - $110 per hour
Mercor is seeking a PyTorch Expert to enhance AI model performance in a remote role. You will guide teams,... ...of experience in ML infrastructure or engineering, including hands-on experience with PyTorch and optimizing GPU kernels. The position offers competitive remuneration...PerformanceRemote jobHourly pay
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to GPU Kernel Engineer for High-Performance AI Inference. Be the first to apply!
- application performance engineer New York, NY
- acting performance New York, NY
- performance coach New York, NY
- performance test architect New York, NY
- lead performance test engineer New York, NY
- performance test engineer New York, NY
- performance engineer New York, NY
- performance improvement consultant New York, NY
- senior performance engineer New York, NY
- senior performance tester New York, NY

