AI Software Engineer Intern
CHN - Minhang, China
CNY 38K-50K (estimate) Entry-level Full Time Internship
Tasks
- Build end to end inference runtime and scheduling
- Develop MoE inference routing and load balancing
- Develop and optimize GPU kernels
- Fuse operators into efficient GPU kernels
- Implement flash attention
- Implement optimized LLM inference techniques
- Implement quantization for model optimization
- Implement speculative decoding
- Optimize KV cache memory and management
- Optimize MoE expert parallelism and sharding
- Optimize NCCL communication
- Profile and tune GPU memory access patterns
- Scale distributed inference across GPUs and nodes
- Study LLM inference research
Perks/Benefits
Skills/Tech-stack
CUDA | Compiler optimization | Continuous batching | Distributed Systems | Dynamic batching | FP8 | FasterTransformer | Flash Attention | GPU Architecture | GPU Kernels | GPU Programming | INT8 | KV cache | Low-bit quantization | MOE | Memory Optimization | Mixture of Experts | NCCL | Operator fusion | Paged Attention | Parallel Computing | Performance Profiling | PyTorch | Python | Quantization | Speculative decoding | TensorRT-LLM | Transformers | Triton | VLLM
Education
Related jobs
-
整车体验数据分析实习生(数据产品与Ai方向) CNY 25K-37KData Modeling | Data Quality | Data Visualization | Data cleaning | Data quality monitoringEntry-level Internship上海5h ago
-
Senior-level Full Time上海、北京7h ago
-
Mid-level Full Time北京 R8h ago
-
Miclaw-端云协同调度专家 (Hybrid AI Architect) CNY 240K-360K5G | API Integration | Claude 3.5 | Distributed Systems | GPT-4oHybrid workSenior-level Full Time北京 R8h ago
-
AAI Intern-Knowledge Governance Solutions CNY 25K-37KData Analysis | Data Visualization | Data cleaning | Excel | Power BIEntry-level Full Time InternshipBeijing, Beijing, China1d ago
-
AI intern CNY 28K-50KAutomated testing | Continuous integration | Deep learning | Generative AI | JavaEntry-level InternshipBeijing,Beijing,China2d ago
-
Senior Deep Learning Solution Architect CNY 240K-480KAccelerated computing | Computer Systems | Data Structures | Deep learning | Distributed TrainingSenior-level Full TimeChina, Beijing2d ago
-
Senior Consultant Specialist (AI Architect/Tech Lead) CNY 144K-192KAPI Design | AWS | Alibaba Cloud | Automation | CI/CDSenior-level Full TimeGuangzhou, Guangdong, China R2d ago
-
Agent systems | Embodied AI | Human Feedback | Language Models | Large Language ModelsMid-level Full Time深圳、上海4d ago
-
Ai 多模态软件工程师(数据飞轮方向) CNY 180K-300KBatch Processing | Data Processing | Feature extraction | Language Models | Large Language ModelsCareer growth | Large-scale project experience | Learning opportunities | Team collaborationMid-level Full Time广州、北京4d ago
-
AI Framework Software Engineer CNY 300K-420KAsynchronous Communication | C++ | Computational graphs | Data parallelism | Deep learningOn-site work environmentEntry-level Full TimeCHN - Minhang, China5d ago
-
Entry-level Internship上海5d ago
-
Embodied AI Research Intern CNY 25K-37KAgentic AI | CLIP | Computer Vision | Deep learning | DeepSpeedEntry-level Full Time Internship深圳、上海5d ago
-
Embodied AI Research Intern CNY 25K-37KAgent planning | Agent reasoning | CLIP | Computer Vision | Data SynthesisInternship experience | Research mentorship | Team collaborationEntry-level Full Time Internship深圳、上海5d ago
-
Embodied AI Research Intern CNY 25K-37KAuto-labeling | CLIP | Computer Vision | Computer Vision Benchmarks | Data SynthesisInternshipEntry-level Full Time Internship深圳、上海5d ago
-
Senior Consultant Specialist (AI Solution Development) CNY 144K-240KAgent systems | Cloud Native | Continuous Delivery | Continuous integration | DockerSenior-level Full TimeGuangzhou, Guangdong, China5d ago
-
3D Perception | C++ | Computer Vision | Deep learning | Foundation ModelsEntry-level Full Time InternshipChina, Shanghai6d ago
-
Artificial Intelligence | Attention Mechanisms | Benchmarking | C++ | GEMMEntry-level Full Time InternshipChina, Beijing6d ago
-
C# | C++ | Data analytics | Deep learning | GPU ComputingComprehensive benefits packageEntry-level Full TimeChina, Shanghai6d ago
-
Entry-level Internship南京6d ago
-
Entry-level Internship南京6d ago
-
AI Agent开发工程师-汽车专项-实习 CNY 25K-37KAPI Design | Authentication | Autogen | Concurrency | Context ManagementEntry-level Internship上海6d ago
-
IT Dept. AI Engineer_Tech. Foundation(上海) CNY 192K-240KAPI Integration | Access Control | Alibaba Cloud | Automation | Cloud servicesMid-level Full TimeShanghai, CN, 2018006d ago
-
Principal Specialist, AI Application CNY 360K-600KAgile | Angular | Cloud Platforms | Enterprise Integration | Generative AISenior-level Full TimeCN-OCG International Center, Cheng Du, China7d ago
-
Principal Specialist, AI Application CNY 360K-600KAgile | Angular | Cloud Computing | Enterprise Integration | Generative AISenior-level Full TimeCN-OCG International Center, Cheng Du, China7d ago