ZipRecruiter

Log In

1

Cuda Kernel Engineer Jobs (NOW HIRING)

quadric, Inc

AI Kernel Engineer (New Grad)

Burlingame, CA · On-site

$120K - $160K/yr

Role The AI Kernel Engineer (New Grad) at Quadric plays a key role in enabling a large number of AI ... CUDA, DSP, NEON, or Triton-lang. * Familiarity with assembly language or compiler internals is a ...

Nvidia

Senior Software Engineer - TensorRT Edge-LLM

Austin, TX · Hybrid

$121K - $160K/yr

Contribute to CUDA kernel and operator development for critical transformer components such as ... Proficient programming ability with modern C++ (C++11/14/17 and beyond). * Familiarity with popular ...

Baseten

Software Engineer - GPU Kernels

New York, NY · On-site

$180K - $360K/yr

THE ROLE We're seeking a GPU Kernel Engineer to join our team at the cutting edge of AI ... Write and optimize code using CUDA, PTX assembly, and architecture-specific techniques * Apply ...

next page

Showing results 1-20

All JobsCuda Kernel Engineer Jobs

Cuda Kernel Engineer information

What are some common challenges faced by Cuda Kernel Engineers when optimizing GPU code for performance?

Cuda Kernel Engineers often encounter challenges such as managing memory hierarchy efficiently, minimizing data transfer between host and device, and avoiding thread divergence. Ensuring optimal occupancy and maximizing parallelism while preventing bottlenecks like bank conflicts or uncoalesced memory access are also key concerns. Collaborating closely with software architects and data scientists is common, as solutions frequently require balancing algorithmic accuracy with hardware limitations. Addressing these challenges requires continuous profiling, testing, and iterative optimization.

What are Cuda Kernel Engineers?

Cuda Kernel Engineers are specialized software developers who design, implement, and optimize parallel computing algorithms using NVIDIA's CUDA platform. They write 'kernels,' which are functions that run on Graphics Processing Units (GPUs) to accelerate computational tasks in areas such as machine learning, scientific simulations, and graphics rendering. These engineers need strong skills in C/C++ programming, GPU architecture, and performance optimization techniques. Their work is crucial for applications that require high-speed data processing and efficient resource utilization.

What are the key skills and qualifications needed to thrive as a CUDA Kernel Engineer, and why are they important?

To thrive as a CUDA Kernel Engineer, you need strong proficiency in C/C++ programming, parallel computing concepts, and a solid foundation in GPU architectures, typically supported by a degree in computer science or a related field. Expertise in NVIDIA CUDA toolkits, GPU profiling tools like Nsight, and familiarity with version control systems are essential. Analytical thinking, problem-solving abilities, and effective collaboration skills help engineers optimize code and work well within development teams. These skills and qualities are crucial for delivering high-performance, scalable GPU solutions in computationally intensive applications.
More about Cuda Kernel Engineer jobs
What cities are hiring for Cuda Kernel Engineer jobs? Cities with the most Cuda Kernel Engineer job openings:
What states have the most Cuda Kernel Engineer jobs? States with the most job openings for Cuda Kernel Engineer jobs include:
What job categories do people searching Cuda Kernel Engineer jobs look for? The top searched job categories for Cuda Kernel Engineer jobs are:
Cuda Kernel Engineer jobs near you
Infographic showing various Cuda Kernel Engineer job openings in the United States as of July 2026, with employment types broken down into 3% Internship, 94% Full Time, and 3% Part Time. Highlights an 82% In-person, and 18% Remote job distribution.
Senior Software Engineer - TensorRT Edge-LLM

Senior Software Engineer - TensorRT Edge-LLM

NVIDIA

Santa Clara, CA • On-site

$143K - $189K/yr

Full-time

Re-posted 27 days ago

Job description

Job Summary:
NVIDIA is a leader in technology innovation, and they are seeking a Senior Software Engineer to join their TensorRT Edge-LLM team. The role involves developing a state-of-the-art inference framework for large language models and optimizing performance for embedded and edge platforms.
Responsibilities:
• Develop and evolve a state-of-the-art inference framework in modern C++ that extends TensorRT with autoregressive model serving capabilities, including speculative decoding, LoRA, MoE, and KV cache management.
• Design and implement compiler and runtime optimizations tailored for transformer-based models running on constrained, real-time platforms.
• Collaborate with teams across CUDA, kernel libraries, compilers, and robotics to deliver high-performance, production-ready solutions.
• Contribute to CUDA kernel and operator development for critical transformer components such as attention, GEMM, and MoE.
• Benchmark, profile, and optimize inference performance across diverse embedded and automotive environments.
• Stay ahead of the rapidly evolving LLM/VLM ecosystem and bring emerging techniques into product-grade software.
Qualifications:
Required:
• BS, MS, PhD, or equivalent experience in Computer Science, Electrical/Computer Engineering, or a closely related field.
• 4+ years of relevant software development experience.
• Deep understanding of transformer models and inference optimization techniques (e.g., quantization, tensor parallelism, or memory-efficient scheduling).
• Proficient programming ability with modern C++ (C++11/14/17 and beyond).
• Familiarity with popular LLM frameworks and libraries such as TensorRT, TensorRT-LLM, vLLM, SGLang, MLC-LLM, or FlashInfer.
• A track record of strong software design, execution, and collaboration across fields.
Preferred:
• Demonstrated development experience or open-source contributions to LLM inference frameworks and libraries, such as SGLang, vLLM, or FlashInfer.
• Proficiency with CUDA, including efficient kernel development, performance profiling, and GPU architecture fundamentals.
• Prior work on autoregressive LLM serving systems, including speculative decoding or KV cache management.
• Familiarity with compiler infrastructure for large language model inference.
• Exposure to robotics or embedded AI pipelines, including optimizing for low-latency, resource-constrained systems.
Company:
NVIDIA is a computing platform company operating at the intersection of graphics, HPC, and AI. Founded in 1993, the company is headquartered in Santa Clara, USA, with a team of 10001+ employees. The company is currently Late Stage.
Nvidia logo

About Nvidia

Sourced by ZipRecruiter

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.

Industry

Computer and electronic product manufacturing

Company size

10,000+ Employees

Headquarters location

Santa Clara, CA, US

Year founded

1993

View All Nvidia Jobs

Apply