大模型算法工程师(开放域对话)
Tasks
- Accelerate inference with vLLM
- Address tool use hallucinations
- Apply DPO
- Apply GRPO
- Apply PPO
- Build end to end dialogue dataset
- Clean and deduplicate raw corpus
- Create evaluation set for complex interaction scenarios
- Develop LLM algorithms for open domain dialogue
- Evaluate with offline benchmarking
- Fine tune base model with SFT
- Implement dialogue state tracking optimization
- Improve multi turn dialogue decision success
- Optimize intent recognition recommendations and task success metrics
- Optimize models with RLHF and RLAIF
- Perform prompt engineering
- Run online A B testing
- Support model quantization and distillation
- Train reward model dataset for reinforcement learning
Perks/Benefits
Skills/Tech-stack
A/B | A/B Testing | B testing | DPO | Data cleaning | Dataset Construction | Deduplication | DeepSpeed | Dialogue State Tracking | Distributed Training | Fine Tuning | Function Calling | GRPO | LLM | Language Models | Large Language Models | Model Distillation | Model Quantization | Offline evaluation | OpenRLHF | PPO | Prompt engineering | Python | RLAIF | RLHF | React | Reinforcement Learning | Reward Model | Reward Modeling | SFT | State tracking | Supervised Fine Tuning | Thought Intermediate Result | Tool use | VLLM
Education
Bachelor of Arts | Bachelor of Engineering | Bachelor of Science
Regions
Countries
States
Related jobs
-
Ai数据闭环研发工程师 CNY 240K-360KData Distribution | Data Distribution Strategy | Data Flywheel | Data Mining | Data evaluationSenior-level Full Time上海、北京4h ago
-
Mid-level Full Time上海4h ago
-
Mid-level Full Time上海5h ago
-
Mid-level Full Time上海5h ago
-
Senior-level Full Time上海5h ago
-
Action models | C++ | Data Generation | Dataset curation | Deep learningSenior-level Full TimeChina, Shanghai23h ago
-
AI运维工程师(大模型推理 / AI Infra) CNY 180K-300KAlerting | Automation | Docker | GPU Acceleration | High AvailabilityEntry-level Full Time深圳1d ago
-
数据算法工程师 CNY 180K-300KAnomaly Detection | Automation | C plus plus | Computer Vision | Data AnnotationEntry-level Full Time上海1d ago
-
Entry-level Full Time上海1d ago
-
Entry-level Full Time上海1d ago
-
Entry-level Full Time上海1d ago
-
Mid-level Full TimeSuzhou, Jiangsu, China1d ago
-
2026 Intern(3 months)-AI Software Enginner CNY 38K-50KAlgorithms | Android | Audio Video Decoding | Audio/Video | C#Entry-level InternshipShenzhen, Guangdong, China1d ago
-
Machine Learning Engineer CNY 248K-315KAndroid | C# | C++ | Embedded System | Embedded System ArchitectureMid-level Full TimeShanghai, Shanghai, China1d ago
-
Entry-level Full TimeShanghai, Shanghai, China1d ago
-
Machine Learning Engineer CNY 216K-300KAI acceleration | Android | C++ | Concurrency optimization | Embedded DevelopmentMid-level Full TimeShenzhen, Guangdong, China1d ago
-
Principal Engineer - Agentic AI Architect CNY 240K-375KAI Deployment | API Design | ASIC | Agent systems | Agentic AISenior-level Full TimeShanghai, China1d ago
-
Sr. Data Engineer CNY 360K-600KAWS | Azure | Cloud Data | Cloud Data Platforms | Data ArchitectureAgile work environmentSenior-level Full TimeChina - Shanghai - Xin Jin …1d ago
-
Software Development Engineer, Data and AI Tech Team CNY 300K-399KAWS Lambda | Amazon EC2 | Amazon S3 | Amazon Web Services | CI/CDCareer growth | Flexible working hours | Inclusive culture | Mentorship | Work-life balanceMid-level Full TimeBeijing, CHN1d ago
-
Mid-level Full TimeBJN01 - Beijing Campus (BJN01), China1d ago
-
自动驾驶数据闭环工程师-Data Infra CNY 25K-37KAI model | C++ | Data Mining | Data Quality | Data Quality EvaluationMid-level Full Time北京、苏州2d ago
-
Mid-level Full Time上海2d ago
-
具身多模态数据分析算法开发实习生 CNY 25K-37KASR | Anomaly Detection | Audio Data | Audio Data Processing | Automated Data LabelingInternship opportunityEntry-level Internship上海2d ago
-
AWQ | AWS | Accelerate | Benchmarking | CUDASenior-level Full TimeGuangzhou, Guangdong, China2d ago
-
Advanced Engineer CNY 360K-600KAI | C# | CAN bus | CCD Camera | Computer VisionCareer growth opportunities | Leadership development | Technical competency development | Training and development programsSenior-level Full TimeNanjing Shi, China2d ago