Inference Systems Backend Engineer - ARK Large Model Platform (Singapore)

Bytedance

Singapore, Singapore

≈ 725,8 тыс.–1,1 млн ₽ · 9,1 тыс.–13,3 тыс. $ · 7,9 тыс.–11,6 тыс. €

11 667 – 17 083 SGD

🏢 Офис

Middle

Полная занятость

Продуктовая

Сингапур

Tech

Описание вакансии

Обязанности

•Apply model quantization

•Collaborate with algorithm teams to optimize models and systems

•Develop large model training and inference systems

•Implement compiler optimization

•Improve compute utilization with elastic scheduling

•Improve high concurrency reliability and scalability

•Integrate GPUs NPUs and TPUs

•Optimize model computation

•Orchestrate tasks across distributed GPU clusters

•Research model training and inference architectures

•Schedule large scale inference traffic

•Tune distributed LLM inference systems

Технологии: Compiler optimization, Deep learning, Distributed Systems, Elastic Scheduling, GPU Computing, GPU scheduling, High Availability, High concurrency, Language Models, Large Language Models, Linux, Machine Learning, Model Quantization, NPU, Python, Scalability, TPU, Task Orchestration