MiniMax

高性能服务研发实习生-2027 届

MiniMax  •  Onsite  •  8 days ago
Apply
AI can make mistakes so check important info. Chat history is never stored.

Job Description

高性能服务研发实习生-2027 届北京、上海校招实习研发 - 后端开发2027届实习生招聘职位描述1. 参与 大模型推理系统 的研发与优化,涵盖执行引擎、批处理调度、缓存与动态并发策略;
2. 优化推理路径性能,提升 吞吐率、延迟与稳定性,探索算力与响应速度的平衡;
3. 设计并实现 推理加速机制(如图计算优化、KV 缓存、高效张量调度等);
4. 参与构建面向 多模态与 Agentic 系统 的推理框架,支撑智能体在真实场景中的快速决策与反馈;
5. 跟踪推理服务的前沿趋势(Speculative Decoding、Context Caching、Dynamic Routing 等),验证其在工程中的落地。职位要求1. 计算机及相关专业,2027 年及以后毕业;
2. 熟悉 Python / C++,具备良好的系统设计与性能分析能力;
3. 理解主流 AI 框架(PyTorch / TensorRT / vLLM / FasterTransformer 等)或推理引擎机制;
4. 对 系统性能优化、分布式服务架构、推理调度 等方向有浓厚兴趣;
5. 若有异步系统、高并发、缓存机制或工程性能调优经验者优先;
6. 能连续实习 3 个月以上,每周出勤至少 4 天。
我们能提供
1. 直面超大规模推理集群的真实系统环境;
2. 与算法、系统、Infra 团队协同优化推理链路的机会;
3. 来自资深系统架构师与模型工程师的 1v1 指导;
4. 若实习表现优异,可转正为全职工程师,共同建设下一代智能推理基础设施。 投递
MiniMax

About MiniMax

MiniMax is a leading global technology company and one of the pioneers of large language models (LLMs) in Asia. Our mission is to build a world where intelligence thrives with everyone.

MiniMax develops proprietary LLMs across various modalities, including a trillion-parameter MoE model, a speech model with low latency and native support for major Asian languages, and a state-of-the-art text-to-speech and text-to-video models. Experience it now at https://hailuoai.com/

Leveraging these multi-modality general-purpose models, the MiniMax API Platform offers enterprises and developers secure, flexible, and reliable API services, enabling the rapid deployment of AI applications.

Industry
IT & Software
Company Size
51-200 employees
Headquarters
Singapore, SG
Year Founded
2022
Social Media