软件工程师 - 大模型端侧优化和部署
Tasks
- Build benchmarking and profiling system
- Deploy large language models on automotive edge chip platform
- Develop CUDA operators for real time inference
- Implement low latency multimodal inference features
- Improve latency throughput and memory efficiency
- Optimize KV cache and sampling methods
- Optimize inference engine and runtime performance
Perks/Benefits
- N/A
Skills/Tech-stack
Attention | Batching | C++ | CUDA | Computational Graph Optimization | Computational graph | Decode | Function Calling | Graph optimization | KV cache | LLM | Linux | Multimodal inference | ONNX Runtime | Operator fusion | Prefill | Python | SGLang | Streaming | Structured Output | TensorRT | TensorRT-LLM | Transformer | VLLM | VLM
Education
Bachelor of Engineering | Bachelor of Science | Master of Science
Roles
Regions
Countries
States
Related jobs
-
功能安全软件工程师Embedded Software Eng.(芜湖) CNY 180K-300KASPICE | Automotive MCU | Automotive SOC | C# | C++Mid-level Full TimeWuhu, CN9h ago
-
Senior Machine Learning Engineer USD 20KData Analysis | Data Visualization | Deep learning | Experimentation | Fraud DetectionCareer growth | Competitive compensation | Open, collaborative cultureSenior-level Full TimeShenzhen, China15h ago
-
Senior Data Engineer / AI Engineer CNY 360K-600KAI Agents | Apache Spark | Azure | Data Modeling | DatabricksSenior-level Full TimeShanghai, Shanghai, China16h ago
-
Operations / IE Special II HKD 360K-550KAPI | C# | Data Loss Prevention | Data Modeling | Data VisualizationMid-level Full TimeHK - Hong Kong (HKCHU), Hong …18h ago
-
算法软件实习生 CNY 25K-37KAutomation Testing | C# | C++ | Computer Vision | Data AnalysisInternship experience | Learning and developmentEntry-level Internship北京1d ago
-
ARM | Android | C++ | Communication Protocols | Digital CommunicationSenior-level Full TimeShanghai, China1d ago
-
AVP - Data and Analytics CNY 300K-420KA/B | A/B Testing | Automation | B testing | Data CleansingFlexible working | Professional developmentExecutive-level Full TimeGuangzhou, Guangdong, China1d ago
-
AVP - Data and Analytics CNY 300K-420KA/B | A/B Testing | Automation | B testing | CRMFlexible working | Inclusive work culture | Professional developmentExecutive-level Full TimeGuangzhou, Guangdong, China1d ago
-
Analyst, Data Science CNY 144K-240KAI Governance | Computer Vision | Data analytics | Deep learning | GitSenior-level Full TimeCN-Dong Bao Building, China1d ago
-
Analyst, Data Science CNY 144K-240KAgile | Artificial Intelligence | Data Science | Deep learning | MLOpsSenior-level Full TimeCN-Dong Bao Building, China1d ago
-
R&D – Voice AI Software Engineer – Windows Platform CNY 300K-420KAI Model Integration | AI model | C# | C++ | Model IntegrationMid-level Full TimeShenzhen, Guangdong, China1d ago
-
Mid-level Full TimeShanghai, Shanghai, China1d ago
-
Mobile Power optimization Engineer CNY 108K-184KAnalog circuit | Analog circuit design | Android | BW Governor | C#Entry-level Full TimeShanghai, Shanghai, China1d ago
-
AI/ML | Agentic Engineering | Apache Airflow | Apache Kafka | Apache NiFiMid-level Full TimeGuangzhou, GD, CN, 5106201d ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous culture | Remote work | Supportive team environmentMid-level Full TimeShenzhen, China2d ago
-
AI Agent算法架构师 CNY 144K-240KAgent Framework | Cloud Computing | Computer Vision | Edge AI | LLM InferenceSenior-level Full Time深圳4d ago
-
Entry-level Full Time北京4d ago
-
Mid-level Full Time上海4d ago
-
Apache Arrow | Data Engineering | Data Mining | Data Processing | Financial DataFast-paced environment | TeamworkMid-level Full TimeShanghai4d ago
-
Mid-level Full TimeBeijing, China4d ago
-
顶尖应届-大模型训练框架研发工程师-MiMo AI 基建 CNY 72K-96KC++ | CUDA | Data loading | DeepSpeed | Distributed ComputingEntry-level Full Time北京4d ago
-
Entry-level Full Time北京4d ago
-
Entry-level Full Time北京4d ago
-
Entry-level Full Time上海4d ago
-
Entry-level Full Time上海4d ago