AI Computing Software Development Engineer, LLM Inference
Tasks
- Collaborate across research and product teams
- Develop inferencing software
- Follow academic developments in AI and large language models
- Perform performance analysis and optimization
- Provide feedback on architecture and hardware design
- Publish results in scientific conferences
- Scale software to multiple platforms
- Tune and benchmark inference performance
Perks/Benefits
- N/A
Skills/Tech-stack
C# | C++ | Debugging | Performance Analysis | PyTorch | Software Design | TensorFlow | Testing
Education
Related jobs
-
Research MLE (Training Optimization)大模型训练优化工程师 CNY 144K-240KC++ | CUDA | DeepSpeed | Distributed Training | FSDPSenior-level Full TimeBeijing, Beijing, China5h ago
-
Entry-level Internship深圳1d ago
-
Ai算法暑期实习生(Llm/强化学习) CNY 37K-37KDPO | Deep learning | Fine Tuning | LLM Fine-tuning | Language ModelsAt least 2 months internship duration | Beijing internship location | Full-time internshipEntry-level Internship北京2d ago
-
Ai算法暑期实习生(Llm/强化学习) CNY 37K-37KDPO | Deep learning | Language Models | Large Language Models | Machine LearningFull-time internship | Internship 2 months or moreEntry-level Internship北京2d ago
-
视觉感知算法工程师 - 榫卯计划 CNY 96K-120K4D reconstruction | C++ | Camera | Computer Vision | Computer Vision DatasetsEntry-level Full Time深圳2d ago
-
Ai算法暑期实习生(Llm/强化学习) CNY 37K-37KDPO | Deep learning | Experimentation | Information Retrieval | Language ModelsContinuous internship 2 months or more | Full-time internship | Location BeijingEntry-level Internship北京2d ago
-
Ai 应用工程师实习生 CNY 36K-37KLangchain | Language Models | Large Language Models | Prompt engineering | PyTorchEntry-level Internship北京2d ago
-
Mid-level Full TimeChina - Hong Kong3d ago
-
CUDA | DeepSpeed | Diffusion Models | Distributed Training | FSDPSenior-level Full TimeBeijing, Beijing, China3d ago
-
LLM Agent Research Scientist 大模型智能体研究科学家 CNY 144K-240KAgent systems | Benchmarking | Cloud Computing | DeepSpeed | GPU ComputingInternship opportunity | Open to all experience levelsEntry-level Full TimeBeijing, Beijing, China3d ago
-
Senior-level Full TimeChina, Shanghai3d ago
-
Deep Learning Compiler Engineer - CUDA CNY 144K-240KC# | C++ | CUDA | Computer Architecture | Distributed communicationComprehensive benefitsSenior-level Full TimeChina, Shanghai3d ago
-
Senior AI Engineer CNY 144K-240KCheckpointing | Distributed Training | Efficient Fine Tuning | Fine Tuning | GPU workload optimizationSenior-level Full TimeBeijing Yizhuang, China3d ago
-
Senior-level Full TimeCHN - Guangzhou - EMS, China3d ago
-
IT Developer Engineer (Phython+AI) CNY 300K-420KArtificial Intelligence | Code review | Debugging | Machine Learning | Production SupportFlexible work hours | In-person collaborationMid-level Full TimeCN004 - Shanghai, China (CN004)3d ago
-
Entry-level Internship广州3d ago
-
Mid-level Full Time深圳3d ago
-
Mid-level Full Time深圳3d ago
-
优才-具身大模型训练框架工程师-觅蜂子公司 CNY 500K-500KC++ | CPU Optimization | CUDA | CUDA graph | Communication overlapMid-level Full Time上海 R3d ago
-
Robotaxi VLA 大模型算法实习生 CNY 25K-37KAutonomous Driving | C++ | Case Development | Data cleaning | Data labelingEntry-level Internship广州3d ago
-
Senior Embedded Software Engineer CNY 360K-600KBSP | Bootloader | Buildroot | C Sharp | C plus plusSenior-level Full TimeShenzhen, Guangdong Province, China4d ago
-
Diffusion Models | Flow matching | GPU Computing | Human Feedback | Multimodal LearningFully remote option | On-site flexibility | Open source collaborationMid-level Full TimeShanghai R4d ago
-
Generative AI - Graphics Engineer CNY 360K-600KBlender | C++ | Computer Graphics | DCC tool scripting | Data PipelinesFully remote option | On-site collaborationSenior-level Full TimeShanghai R4d ago
-
Mid-level Full Time北京4d ago
-
Mid-level Full Time北京4d ago