SciforiumSan Francisco, CAFull-timeHybridPosted 26 days ago
$190k–$250k/yr listed by the employer
About the typical $210k a year for senior Software Engineer jobs in CaliforniaHow we compare
How we compare. Typical is the median yearly pay of 1,291 senior Software Engineer jobs in California that list pay, from the employers' own postings. About means within 5%.
Key facts
Experience
5+ years
Degree
Bachelor's degree
This job is closed.
The employer took it down 15 days ago, after 5 days open. Here are similar open jobs.
Checked: On the company's own careers siteAshby board
Design, implement, and optimize custom GPU kernels for AI workloads.
Profile ML operations and improve performance for large-scale LLM training and inference.
Integrate optimized kernels into PyTorch, JAX, and internal runtimes.
Build performance models, identify bottlenecks, and develop tooling, benchmarks, documentation, and tests.
Summarised from the posting by AI and can be wrong. The full description is the source.
Requirements
Experience
5+ years of industry or research experience in GPU kernel development or high-performance computing
Hands-on experience with Triton and/or JAX Pallas for custom kernel development
Extensive experience writing and optimizing custom GPU kernels in C++ and PTX
Proven ability to integrate low-level kernels into PyTorch, JAX, or similar frameworks
Experience working with large-scale LLM workloads (training or inference)
Experience with AMD GPUs and ROCm optimization (preferred)
Experience with efficient model-serving frameworks such as vLLM or TensorRT (preferred)
Experience with TPUs, XLA, or similar accelerator programming environments (preferred)
Contributions to open-source ML systems, compilers, or GPU kernels (preferred)
Education
Bachelor’s, Master’s, or PhD in Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics, or a related field
Skills
Strong programming skills in C++ and Python, and familiarity with ML frameworks
Deep expertise in CUDA/ROCm, GPU memory models, and performance optimization strategies
Strong understanding of PTX, GPU ASM, and low-level GPU execution
Familiarity with JAX FFI and custom ML operator development (preferred)
Benefits
Health insurance
Medical insurance
Dental & vision
Dental and vision insurance
Retirement plan
401(k) plan
Paid time off
Flexible time off
Equity
Competitive salary and equity
Meals
Daily lunch, snacks, and beverages
Full job description
From Sciforium’s careers site
Sciforium is an AI infrastructure company developing next-generation multimodal AI models and a proprietary, high-efficiency serving platform. Backed by multi-million-dollar funding and direct sponsorship from AMD with hands-on support from AMD engineers the team is scaling rapidly to build the full stack powering frontier AI models and real-time applications.
ABOUT THE ROLE
Show full descriptionShow less
We are seeking a highly skilled GPU Kernel Engineer who is passionate about pushing the limits of performance on modern accelerators. In this role, you will design and optimize custom GPU kernels that power next-generation large-scale AI systems. You will work across the hardware–software stack, from low-level kernel development to integrating optimized ops into high-level ML frameworks used for large-scale training and inference.
This role is ideal for someone who thrives at the intersection of GPU programming, systems engineering, and cutting-edge AI workloads, and who wants to make meaningful contributions to the efficiency and scalability of our ML platform.
KEY RESPONSIBILITIES
Design, implement, and optimize custom GPU kernels using C++, PTX, CUDA, ROCm, Triton, and/or JAX Pallas.
Profile and optimize end-to-end performance of ML operations, with a focus on large-scale LLM training and inference.
Integrate low-level GPU kernels into frameworks such as PyTorch, JAX, and custom internal runtimes.
Develop performance models, identify bottlenecks, and deliver kernel-level improvements that significantly accelerate AI workloads.
Collaborate with ML researchers, distributed systems engineers, and model-serving teams to optimize compute performance across the stack.
Work closely with hardware vendors (NVIDIA/AMD) and stay current on the latest GPU architecture capabilities and compiler/toolchain improvements.
Contribute to tooling, documentation, benchmarking suites, and testing frameworks to ensure correctness and performance reproducibility.
MUST-HAVES
5+ years of industry or research experience in GPU kernel development or high-performance computing.
Bachelor’s, Master’s, or PhD in Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics, or a related field.
Strong programming skills in C++, Python, and familiarity with ML frameworks.
Deep expertise in CUDA/ROCm, GPU memory models, and performance optimization strategies.
Hands-on experience with Triton and/or JAX Pallas for custom kernel development.
Strong understanding of PTX, GPU ASM, and low-level GPU execution.
Extensive experience writing and optimizing custom GPU kernels in C++ and PTX.
Proven ability to integrate low-level kernels into PyTorch, JAX, or similar frameworks.
Experience working with large-scale LLM workloads (training or inference).
NICE-TO-HAVES
Experience with AMD GPUs and ROCm optimization.
Familiarity with JAX FFI and custom ML operator development.
Experience with efficient model serving frameworks (e.g., vLLM, TensorRT).
Experience with TPUs, XLA, or similar accelerator programming environments.
Contributions to open-source ML systems, compilers, or GPU kernels.
BENEFITS INCLUDE
Medical, dental, and vision insurance
401k plan
Daily lunch, snacks, and beverages
Flexible time off
Competitive salary and equity
EQUAL OPPORTUNITY
Sciforium is an equal opportunity employer. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status.