AI Software Engineer Intern
CHN - Minhang, China
CNY 38K-50K (estimate) Entry-level Full Time Internship
Tasks
- Apply model quantization
- Build MoE routing and load balancing
- Develop GPU kernels for tensor workloads
- Develop speculative decoding
- Implement expert parallelism and sharding
- Implement flash attention and paged attention
- Implement optimized LLM inference techniques
- Implement runtime scheduling and batching
- Integrate end to end inference stack
- Optimize KV cache and memory management
- Optimize distributed inference communication
- Optimize memory access patterns
- Perform operator fusion and kernel efficiency tuning
- Study LLM inference research
- Tune multi GPU multi node performance
Perks/Benefits
Skills/Tech-stack
CUDA | Distributed Systems | FP8 | FasterTransformer | Flash Attention | GPU Architecture | GPU Programming | INT8 | KV cache | Low-bit quantization | MOE | Memory Management | 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
-
Entry-level Full Time北京 R4h ago
-
Miclaw-端云协同调度专家 (Hybrid AI Architect) CNY 240K-480K5G | Cloud Computing | Consistency protocols | Data Compression | Distributed SystemsHybrid work modelSenior-level Full Time北京 R4h ago
-
Entry-level Full Time北京 R6h ago
-
Senior-level Full Time北京6h ago
-
机器人VLA算法研究员 - XiaomiRobotics CNY 500K-500KDeep learning | Diffusion Models | Language Models | Machine Learning | Mixture of ExpertsEntry-level Full Time北京6h ago
-
Mid-level Full Time北京 R6h ago
-
Mid-level Full Time北京 R6h ago
-
IT Dept. AI Engineer_Application (上海) CNY 240K-360KAI machine learning | Alibaba Cloud | Cloud Applications | Database Design | Language ModelsMid-level Full TimeAnting, CN, 2018051d ago
-
Sr Machine Learning Engineer III CNY 240K-480KAPI Design | AWS | Agent Frameworks | Azure DevOps | CI/CDAdoption leave | Annual Medical Checkup | Family leave | Flexible benefits | Life insuranceSenior-level Full TimeChina-Shanghai (Tianshan-W-Rd)1d ago
-
AI Software Engineer Intern CNY 38K-50KCUDA | Compiler optimization | Continuous batching | Distributed Systems | Dynamic batchingOn-site workEntry-level Full Time InternshipCHN - Minhang, China1d ago
-
AI Software Engineer Intern CNY 28K-50KAWQ | Cache optimization | DINOv2 | DeepSpeed | Diffusion ModelsEntry-level Full Time InternshipCHN - Minhang, China1d ago
-
Entry-level Full Time InternshipCHN - Minhang, China1d ago
-
Ai多模态研究实习生(有留用机会) CNY 25K-37KClustering | DBSCAN | Data Visualization | Embeddings | FaissMentorship | Real world production data exposure | Return OfferEntry-level Internship广州、北京1d ago
-
Mid-level Full Time上海1d ago
-
Ai多模态研究实习生(有留用机会) CNY 25K-37KAttention | Clustering | DBSCAN | Data Visualization | EmbeddingsConversion to full time offer | Mentorship | On-the-job trainingEntry-level Internship广州、北京1d ago
-
Entry-level Full Time广州1d ago
-
Ai多模态研究实习生(有留用机会) CNY 25K-37KAttention Mechanisms | Clustering | DBSCAN | Data Analysis | Data ProcessingCareer growth | Full-time conversion opportunity | Mentorship | Real world production dataEntry-level Internship广州、北京1d ago
-
Mid-level Full TimeAIA ED (Shanghai) Hongkou, China2d ago
-
C++ | CUDA | Embodied AI | GPU Computing | LinuxCompetitive salary | Comprehensive benefits packageMid-level Full TimeChina, Shanghai2d ago
-
Ai算法暑期实习生(Llm/强化学习) CNY 36K-37KDPO | Deep learning | Language Models | Large Language Models | Machine LearningFull-time internship | On-site internshipEntry-level Internship北京2d ago
-
Mid-level Full Time深圳、上海2d ago
-
实习-AI模型使用(Safety服务方向) CNY 25K-37KAdversarial Attacks | CI/CD | CNN | Data poisoning | Deep learningEntry-level Internship上海2d ago
-
实习-Ai研究员-大语言模型/视觉语言模型算法与后训练(博士优先) CNY 25K-37KAI Feedback | Direct Preference Optimization | Efficient Fine Tuning | Fine Tuning | FlaxEntry-level Internship上海2d ago
-
Ai算法暑期实习生(Llm/强化学习) CNY 36K-37KDPO | Deep learning | Language Models | Large Language Models | Machine LearningFull-time internship | Onsite internshipEntry-level Internship北京2d ago
-
Executive-level Full TimeHangzhou, China3d ago