Miclaw-大模型训练推理方向实习生
Tasks
- Collaborate with model system and chip teams
- Convert research into production engineering solutions
- Evaluate model performance in edge scenarios
- Explore edge friendly MoE inference strategies
- Implement model chip co design for joint optimization
- Optimize KV cache and attention for long context
- Reproduce state of the art inference techniques
- Research large model inference optimization
Perks/Benefits
- N/A
Skills/Tech-stack
Attention | C++ | CUDA | Compiler optimization | Deep learning | FlashAttention | High Performance | High-Performance Computing | INT4) | INT8 | KV cache | Machine Learning | Model Compression | Parallel Computing | Performance Computing | Performance optimization | Python | Quantization | Sparse attention | Speculative decoding
Education
Roles
AI | AI Research Intern | Intern | Research Intern | Software Engineer | Software Engineer Intern
Related jobs
-
Manager, AI / Data Scientist CNY 240K-360KClustering | Convolutional Neural Network | Data Quality | Decision Tree | Deep learningMid-level Full TimeAIA ED (Shanghai) Hongkou, China1d ago
-
Analog circuit | Analog circuit design | Brushless Motor | Brushless motor control | C#Mid-level Full TimeDongguan (R&D), China1d ago
-
AI Engineer CNY 240K-360KAI workflow | AI workflow design | Agent systems | Computer Vision | Data AnnotationOccasional travel | Office environmentSenior-level Full TimeChina - Suzhou, Jiangsu - 297 …1d ago
-
Mid-level Full Time北京 R2d ago
-
数据开发工程师(AI Agent方向) CNY 216K-360KAPI Development | AST | Data Dictionary | Data Governance | Data ModelingMid-level Full TimeBeijing2d ago
-
Ai数据工程实习生(训练数据 & 清洗方向) CNY 25K-37KData Deidentification | Data Pipelines | Data Quality | Data Quality Management | Data StandardizationInternship experience | MentorshipEntry-level Internship上海2d ago
-
AWS | Access Control | Apache Iceberg | Authentication | AzureEmployee networks | Flexible work/life support | Inclusive development opportunities | Paid volunteer daysSenior-level Full TimeHangzhou, China2d ago
-
AI Model Inference | AI model | Agent Framework | C++ | Closed LoopEntry-level Full Time InternshipChina, Shenzhen2d ago
-
Automated testing | C# | C++ | Datalink communication | DebuggingEmployee assistance programs | Flexible spending accounts | Health Lifestyle Programs | Health savings account | Life insuranceMid-level Full TimeWuxi, Jiangsu, China2d ago
-
Senior-level Full Time北京、苏州3d ago
-
Mid-level Full Time北京、上海、苏州3d ago
-
Entry-level Full Time深圳3d ago
-
Senior-level Full Time上海3d ago
-
AI Intern – RAG Engineering CNY 37K-37KDify | Document processing | LLM Applications | Langchain | LanggraphEntry-level Full Time Internship北京市, 北京市, 中国3d ago
-
AI Intern – Agent & LLM Solutions CNY 45K-57KDify | Langchain | Langgraph | Language Models | Large Language ModelsEntry-level Full Time Internship北京市, 北京市, 中国3d ago
-
Agent Frameworks | Boundary testing | Case design | Data Privacy | Data anonymizationEntry-level Full Time InternshipBeijing, Beijing, China3d ago
-
Applied AI Engineer - Silicon Co-Design Group CNY 300K-480KAgent Framework | Autogen | C# | C++ | CrewAISenior-level Full TimeChina, Shanghai3d ago
-
Senior-level Full TimeChina, Shanghai3d ago
-
Senior Machine Learning Engineer II CNY 240K-480KAPI Integration | AWS | Agent Framework | Azure DevOps | CI/CDAnnual Medical Checkup | Family care leave | Flexible benefits | Life insurance | Long service awardSenior-level Full TimeChina-Shanghai (Tianshan-W-Rd)3d ago
-
Mid-level Full Time北京 R5d ago
-
Miclaw-端云协同调度专家 (Hybrid AI Architect) CNY 240K-480KCloud Computing | Consistency protocols | Data Compression | Distributed Systems | Edge ComputingHybrid workSenior-level Full Time北京 R5d ago
-
None Full Time深圳、北京、上海6d ago
-
Entry-level Full Time深圳、北京、上海6d ago
-
Head of AI Innovation - Shenzhen CNY 420K-552KAccess Control | Anomaly Detection | Benchmarking | Classification | Data PipelinesExecutive-level Full TimeShenzhen6d ago
-
C++ | Channel coding | Communication Systems | DSP Toolbox | MATLABEntry-level Internship Part TimeShanghai (JingAn), China6d ago