Full-Time
CUDA Kernel Engineer & Researcher
Confirmed live in the last 24 hours
xAI
51-200 employees
AI tools for research and information retrieval
Compensation Overview
$180k - $440kAnnually
Mid, Senior
Palo Alto, CA, USA + 1 more
- Developing and improving low-level CUDA kernel optimizations for state-of-the-art inference and training software stack.
- Profiling, debugging, and optimizing single and multi-GPU operations using tools such as Nsight.
- Understanding GPU memory hierarchy and computation capabilities.
- Implementing the latest methods from the deep learning literature in low-level CUDA kernels.
- Innovating new ideas that bring us closer to the limits of a GPU.
- Building high-performance GeMM CUDA kernels using Tensor cores or CUDA cores from scratch or by utilizing CuTe/CUTLASS.
- Implementing features for attention kernel by extending existing kernels or writing them from scratch.
- Comfortable with writing both forward and backward kernels and ensuring its correctness while considering floating point errors.
- Optimizing for both memory-bound and compute-bound operations.
- Reasoning about register pressure, shared-memory usage and GPU utilization through tools such as Nsight and removing bottlenecks.
- Being familiar with the latest and the most effective techniques in optimizing inference and training workloads.
- Using pybind to integrate custom-written kernels into a framework, specially JAX/XLA.
- Developing and improving low-level CUDA kernel optimizations for state-of-the-art inference and training software stack.
- Profiling, debugging, and optimizing single and multi-GPU operations using tools such as Nsight.
- Understanding GPU memory hierarchy and computation capabilities.
- Implementing the latest methods from the deep learning literature in low-level CUDA kernels.
- Innovating new ideas that bring us closer to the limits of a GPU.
x.ai develops advanced artificial intelligence tools aimed at enhancing research and information retrieval. Its main product, Grok, is designed to answer a variety of questions, including unconventional ones that other AI systems may not handle. Grok provides real-time knowledge, making it a useful resource for researchers, academics, and professionals who need quick access to relevant information. Unlike its competitors, Grok stands out for its ability to suggest questions and provide nuanced answers, catering to users seeking both straightforward and complex information. The company's goal is to empower users by streamlining their research processes and fostering innovation through reliable data processing capabilities.
Company Stage
M&A
Total Funding
$5.2B
Headquarters
Burlingame, California
Founded
2023
6 month growth
↑ 192%1 year growth
↑ 2772%2 year growth
↑ 31500%
Simplify's Take
What believers are saying
- The $2 million investment from HealWell AI indicates strong financial backing and potential for growth in the healthcare sector.
- Collaborations with industry leaders like Nvidia and Dell enhance x.ai's technological capabilities, making it a frontrunner in AI-driven research.
- Grok's unique features and continuous improvement through user feedback can attract a diverse and expanding user base, increasing subscription and licensing revenues.
What critics are saying
- The competitive landscape of AI-driven research tools is fierce, with giants like OpenAI posing significant threats.
- Elon Musk's controversial decisions and public statements could impact x.ai's reputation and stakeholder trust.
What makes xAI unique
- Grok's ability to answer unconventional or 'spicy' questions sets it apart from other AI tools that may avoid such queries.
- x.ai's focus on real-time knowledge and user feedback ensures that Grok evolves continuously, maintaining its relevance and utility.
- The strategic partnerships with tech giants like Nvidia and Dell for building the world's largest supercomputer provide x.ai with unparalleled computational power.