Research Engineer - AI Systems

We are seeking a highly motivated AI Systems Research Engineer specializing in Trainium, GPU kernels, and LLM systems optimization. You will work at the intersection of AI Systems, Compiler and Runtime Optimization, Distributed Training & Inference, GPU/Accelerator Kernel Development, and Large Language Model Infrastructure. Your work will directly impact the scalability and performance of AI applications deployed on our platform., * Design and implement high-performance kernels for Attention, MoE, GEMM, collective communication, and quantization.

• Optimize kernels for NVIDIA, AMD, and AWS Trainium.
• Develop custom operators and graph optimizations using Neuron SDK, PyTorch/XLA, Torch Dynamo, and Neuron Compiler.
• Improve performance of vLLM, SGLang, TensorRT-LLM, and custom inference runtimes.
• Design scalable distributed training and inference solutions across thousands of accelerators.
• Contribute to open-source projects, publish technical findings and engage with the developer community.

• Proficiency in AI programming languages such as Python and C++.
• Deep understanding of GPU architecture and performance optimization.
• Experience with CUDA, Triton, ROCm/HIP, or AWS Neuron.
• Strong understanding of AI frameworks (e.g., PyTorch, Dynamo, LMCache), model architectures and profiling tools (e.g. Nsight, ROCm Profiler, or Neuron Profiler).
• Strong problem-solving skills and the ability to work in a collaborative, remote environment.
• A background in computer science, engineering, or a related field is preferred.

Preferred Experience

• Contributions to open-source AI infra projects like vLLM, SGLang, PyTorch, or Triton.
• Experience with with FlashAttention, PagedAttention, MoE, RLHF, or distributed AI systems.
• Publications in top-tier conferences like MLSys, OSDI, SOSP, NSDI, SC, HPCA, or ISCA

• Be part of a visionary team aiming to redefine AI infrastructure and influence the future of multi-silicon AI computing.
• Work on cutting-edge technologies that solves frontier AI infrastructure problems.
• Collaborate with experts from leading institutions and tech companies.
• Competitive compensation with equity. Enjoy a flexible, remote work environment that values innovation and autonomy.

Yotta Labs is building the next generation multi-silicon AI cloud and runtime platform to power the world’s most demanding AI workloads. We enable training and inference across NVIDIA GPUs, AMD GPUs, and AWS Trainium, helping AI companies achieve the best performance and economics across heterogeneous hardware. Our mission is to provide high-performance AI computing and Model API services, enabling AI companies, research labs, and enterprises to train, deploy and integrate cutting-edge models at scale.