llm服务部署工程师
Tasks
- Build LLM service CI CD pipeline
- Create standardized preprocessing training evaluation and deployment workflow for fine tune
- Develop edge LLM inference service pipeline
- Develop load testing backtesting accuracy troubleshooting and service call tools
- Implement model quantization and compilation optimizations
- Integrate and deploy LLM from pretrained model to edge inference service
- Integrate inference engines and run performance testing
- Optimize inference latency and memory usage on edge devices
- Package and version and deploy inference services
- Provide performance monitoring logging tracing and error diagnosis
Perks/Benefits
- N/A
Skills/Tech-stack
AWQ | Agent systems | As-a-Service | C++ | CI/CD | Eagle | Edge Computing | Fine Tuning | GPTQ | Gguf | Huggingface | INT4) | INT8 | Inference Optimization | Jetson Nano | Jetson Xavier | LoRA | Load Testing | Medusa | Model Compression | Model Quantization | Model-as-a-Service | Nano-LLM | Performance Testing | PyTorch | Python | QLoRA | RadixAttention | SGLang | Structured generation | Transformers | VLLM
Education
Regions
Countries
States
Related jobs
-
Senior-level Full TimeShanghai, China2h ago
-
Automation & Robotics Engineer CNY 360K-600KActuator integration | Analog Signal | Artificial Intelligence | C++ | CADSenior-level Full TimeHangzhou, China14h ago
-
Senior-level Full Time上海、北京18h ago
-
Entry-level Internship上海18h ago
-
Mid-level Full Time上海、深圳 R18h ago
-
Entry-level Full Time上海18h ago
-
Ego-Centric视觉感知算法工程师 CNY 180K-300K2D Segmentation | 3D Gaussian Splatting | 3D Hand Pose | 3D Reconstruction | 6D PoseMid-level Full Time上海、北京 R18h ago
-
Mid-level Full TimeBeijing19h ago
-
资深机器视觉专家 CNY 180K-300KComputer Vision | Deep learning | Docker | Image Segmentation | Image classificationMid-level Full Time北京、上海20h ago
-
Entry-level Full Time北京20h ago
-
Database Administrator (DBA / DBRE) - Cloud Database Operations & Reliability Engineering USD 140K-200KAWS Aurora | AWS RDS | Auditing | Backup | Cloud SQLH1B sponsorshipSenior-level Full Time圣克拉拉20h ago
-
Software Engineer - Generative AI & ML CNY 144K-240KAWS | Agent Orchestration | CI/CD | Cloud platform | Data PreprocessingSenior-level Full TimeShanghai1d ago
-
Site Reliability Engineer, Ai & Data Platforms CNY 144K-240KAnsible | Apache Airflow | Apache Spark | Argo CD | BashOn-call rotationSenior-level Full TimeShanghai1d ago
-
Consultant Specialist (GenAI Agent Platform) CNY 300K-420KAWS | Access Control | Agent Orchestration | Audit Logging | AzureEntry-level Full TimeGuangzhou, Guangdong, China R1d ago
-
Senior-level Full TimeShanghai1d ago
-
Mid-level Full TimeShanghai, Shanghai, China1d ago
-
Mid-level Full TimeQingpu, Shanghai, China1d ago
-
APIs | AWS | Agent Orchestration | Agent systems | AzureMid-level Full TimeShenzhen, Guangdong, China R1d ago
-
机器&学习&AI Machine Learning & AI Eng. CNY 300K-420KAI Agents | Artificial Intelligence | Cloud services | Continuous Monitoring | Data QualityMid-level Full TimeAnting, CN, 2018051d ago
-
Data Analytics & Management, Officer CNY 144K-240KAgentic AI | Alteryx | Anomaly Detection | Auditability | BCBS 239Employee networks | Flexible work/life support | Inclusive development opportunities | Paid volunteer daysSenior-level Full TimeHangzhou, China1d ago
-
Mid-level Full TimeChina Shanghai1d ago
-
ASIC physical design | C++ | C++14 | Distributed Computing | High PerformanceEntry-level Full TimeChina, Shanghai1d ago
-
AWS CDK | AWS CloudFormation | AWS CloudWatch | AWS Lambda | AWS SecretsOn-call rotationEntry-level Full TimeBeijing, CHN1d ago
-
Entry-level Internship Part TimeWuxi, Jiangsu, China1d ago
-
Action Model | Action Transformer | Autonomous Navigation | Computer Vision | Embedded SoftwareMid-level Full TimeBeijing, China1d ago