大模型 Infra 研发实习生(Agentic RL 方向)
Tasks
- Build distributed rollout and evaluation scheduler
- Design task environment abstraction layer
- Develop agent trajectory data pipeline
- Diagnose bottlenecks and improve scalability
- Implement tracing and observability for system reliability
- Integrate experiment management monitoring and alerting
Perks/Benefits
Skills/Tech-stack
Asynchronous programming | Concurrency | Distributed Systems | Docker | Git | Gymnasium | Kubernetes | Linux | Make | OpenAI Gym | PPO | Python | RLAIF | RLHF | Ray | Reinforcement Learning | SGLang | Shell | Slurm | VLLM
Education
N/A
Related jobs
-
Mid-level Full Time深圳3h ago
-
Entry-level Internship北京4h ago
-
AI intern CNY 28K-50KAutomated testing | Continuous integration | Deep learning | Generative AI | JavaEntry-level InternshipBeijing,Beijing,China20h ago
-
Intelligent Test Automation & GenAI Tool Engineer CNY 360K-540KAgent systems | C# | C++ | CI/CD | ConfluenceSenior-level Full TimeShanghai, Shanghai, China23h ago
-
Sr. AI Process Engineer, Seller Compliance CNY 360K-600KAWS | CI/CD | Data Pipelines | Deployment | Feature StoreSenior-level Full TimeShanghai, CHN1d ago
-
Ai数据后端工程师(实习生) CNY 25K-37KAlgorithms | Data Structures | Distributed Systems | ELK | GoInternship | Learning opportunities | MentorshipEntry-level Internship上海2d ago
-
Entry-level Full Time上海2d ago
-
数据算法工程师(实习生) CNY 25K-37KC++ | Computer Vision | Data Generation | Data Preprocessing | Data cleaningInternshipEntry-level Internship上海2d ago
-
Entry-level Full Time上海3d ago
-
Mid-level Full Time广州 R3d ago
-
Mid-level Full Time广州3d ago
-
Mid-level Full Time深圳、上海、北京、中国香港3d ago
-
机器学习工程师 – 模型推理优化 CNY 180K-300KModel Distillation | Model Pruning | Model Quantization | Model Sparsity | ONNXEntry-level Full Time北京3d ago
-
Mid-level Full Time深圳、上海、北京、中国香港3d 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、北京3d ago
-
Mid-level Full Time深圳、上海、北京、中国香港3d ago
-
Entry-level Full Time深圳、北京、上海3d ago
-
Entry-level Full Time深圳、北京、上海3d ago
-
大语言模型后训练算法工程师 CNY 240K-480KDistributed Training | Docker | Fine Tuning | Human Feedback | KubernetesMid-level Full Time深圳、上海3d ago
-
Senior-level Full Time广州3d ago
-
数据平台开发工程师 CNY 180K-360KCode Refactoring | Data Governance | Data Lake | Data Modeling | Data WarehouseMid-level Full Time广州3d ago
-
Senior-level Full Time上海、深圳3d ago
-
Senior Consultant Specialist (RAG Backend Developer) CNY 144K-240KA/B | A/B Testing | ABAC | Audit Logging | B testingSenior-level Full TimeGuangzhou, Guangdong, China3d ago
-
AWQ | AWS | Batching | CPU architecture | CUDASenior-level Full TimeGuangzhou, Guangdong, China3d ago
-
Sr. AI Process Engineer, Seller Compliance CNY 360K-600KAWS | CI/CD | Code review | Data Pipelines | DocumentationSenior-level Full TimeShanghai, CHN3d ago