Job Details
Location: Across United States
Salary: Not specified
Company: ApnaWorker
At SparseMindAI, we are building the next generation of ultra-sparse AI systems that make large-scale machine learning more efficient, sustainable, and deployable. We are looking for a Sparsity Framework Engineer to help transform cutting-edge sparse training research into a developer-friendly framework that enables sparse pretraining and retraining, model benchmarking and evaluation, hardware-aware sparsification, efficient inference deployment, and simple APIs for loading, training, optimizing, and exporting sparse models. This role sits at the intersection of machine learning engineering, LLM systems, sparse training, and software architecture. Ideal candidates should have experience with PyTorch, deep learning systems, ML training and inference pipelines, building reusable frameworks, LLM infrastructure such as vLLM and DeepSpeed, and CUDA sparse kernels. We offer a remote-friendly work environment, flexible hours, unlimited PTO, collaboration with Tsinghua University research lab, and significant product ownership. Send CV to careers@sparsemindai.com.