LLM/VLM Inference Optimization Engineer

ByteDance in San Jose is looking for a Research Engineer specializing in LLM/VLM inference optimization. You will design and optimize high-performance systems, and collaborate closely with research teams to streamline model performance for large-scale deployments. The ideal candidate has a strong foundation in C/C++, Python, and machine learning frameworks. This role offers a competitive salary range from $244,800 to $450,000 annually, with benefits including health insurance, 401(k), and paid personal time. #J-18808-Ljbffr