大模型 Infra 研发实习生（Agentic RL 方向）
Tasks
- Build parallel rollout and evaluation scheduler
- Build visualization for failure case diagnostics
- Design task environment abstraction layer
- Develop agent trajectory data pipeline
- Ensure observability and recoverability under large workloads
- Implement data storage retrieval replay versioning
- Improve throughput and resource utilization
- Integrate experiment management monitoring alerting and tracing
- Integrate heterogeneous environments
Perks/Benefits
- N/A
Skills/Tech-stack
Alerting | Asynchronous programming | Concurrency | Data pipeline | Distributed Systems | Distributed tracing | Docker | Git | Gymnasium | Kubernetes | Language Models | Large Language Models | Linux | Make | Monitoring | Mujoco | Observability | OpenAI Gym | PPO | PPO GRPO | Python | RLAIF | RLHF | Ray | Reinforcement Learning | Retrieval | SGLang | Shell | Slurm | Storage | Task Environment Abstraction | VLLM | Version control
Education
N/A
Related jobs
-
Entry-level Full Time北京3h ago
-
大语言模型后训练/Agentic算法工程师 CNY 180K-360KAgentic RL | DAPO | Distributed Training | Function Calling | GRPOEntry-level Full Time上海、北京3h ago
-
大模型 Infra 研发实习生（Agentic RL 方向） CNY 25K-37KAsynchronous programming | Concurrency | Distributed Systems | Docker | GitFlexible work schedule | Internship opportunity | MentorshipEntry-level Internship深圳3h ago
-
Entry-level Full Time北京、上海3h ago
-
AGI 服务端资深工程师-Talkie&星野 CNY 180K-300KData Engineering | Dify | Distributed Systems | Go | Inference OptimizationMid-level Full Time北京、上海3h ago
-
Mid-level Full TimeBeijing, China19h ago
-
Mid-level Full TimeChina Shanghai21h ago
-
Asynchronous programming | Dashboards | Data Observability | Data Validation | DatabasesMid-level Full TimeChina, Shanghai21h ago
-
Senior-level Full TimeWuxi, Jiangsu, China1d ago
-
Entry-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++ | Data Generation | Data Modeling | Data Transformation | Data cleaningInternshipEntry-level Internship上海2d ago
-
Llm算法实习生（具身大脑方向） CNY 25K-37KAgentic RL | Data Annotation | Fine Tuning | Human Feedback | LLM AgentEntry-level Internship深圳3d ago
-
Llm算法实习生（具身大脑方向） CNY 25K-37KAgentic RL | Data Modeling | LLM Agent | Language Models | Large Language ModelsInternship experience | Mentorship | Research collaborationEntry-level Internship深圳3d ago
-
Llm算法实习生（具身大脑方向） CNY 25K-37KEmbodied AI | Fine Tuning | Human Feedback | LLM Agents | Language ModelsEntry-level Internship深圳3d ago
-
nlp算法工程师-2027届 CNY 25K-37KDeep learning | DeepSpeed | Fine Tuning | Information Retrieval | Language ProcessingEntry-level Internship武汉3d ago
-
AI Agent Engineer(Embededd Software Tooling)_ETAS CNY 240K-480KAgent architecture | C++ | Deep learning | Edge AI | Embedded SoftwareSenior-level Full TimeShanghai, Shanghai, China3d ago
-
AI Application Development Engineer CNY 180K-300KAgent systems | Artificial Intelligence | Computer Vision | Deep learning | Image ProcessingEntry-level Full TimeShenzhen, Guangdong Province, China3d ago
-
Access Control | Alerting | BigQuery | DBT | Data GovernanceAutonomy | Growth opportunities | High-impact work | TrustMid-level Full TimeChina3d ago
-
Senior-level Full TimeChina Shanghai3d ago
-
APIs | AWS | Agentic Workflows | Azure | Cloud platformSenior-level Full TimeChina, Shanghai3d ago
-
Senior Platform AI Engineer - Silicon Co-Design Group CNY 360K-540KAuthentication | Authorization | C# | C++ | CachingComprehensive benefits package | Family benefitsSenior-level Full TimeChina, Shanghai3d ago
-
Entry-level Full TimeCN-Beijing-Office, China3d ago
-
Mid-level Full TimeShanghai, CN, 2012033d ago
-
具身智能数据开发实习生 CNY 25K-37KAPI Development | Algorithms | Automation | Data Ingestion | Data StructuresEntry-level Internship上海4d ago