安德烈斯蒂尔动力工具(青岛)有限公司
云端多模态大模型工程师-[649998]
Skills
4 months ago
Share this opportunity
Share this opportunity to other talents of your network:
✓ Offer them a visibility boost with clients.
✓ Help your contacts find their next job.
Important information
Contract type:
Permanent
Location:
Suzhou, Jiangsu, China
Work mode:
Onsite
Published on:
13 August 2026
What they need
该职位来源于猎聘 岗位职责
负责云端多模态大模型(LLM / VLM)的训练、微调与评估;
负责大模型在云端的部署、推理优化与服务化(API化);
设计并实现云端大模型与本地小模型之间的通信与协同机制(如蒸馏、路由、分层推理等);
基于 AWS(如 EC2、S3、EKS、ECR 等)搭建与维护训练与推理基础设施;
负责模型性能优化,包括推理加速(TensorRT / vLLM / quantization 等);
参与多模态数据处理(图像、文本、语音等)与训练管道建设。
任职要求
计算机、人工智能或相关专业;
熟悉 PyTorch / Deep Learning 训练框架;
熟悉大模型训练或微调(LLM / Vision-Language Model);
熟悉模型部署与推理服务(FastAPI / Triton / vLLM 等);
熟悉 AWS 云平台(EC2、S3、EKS、IAM、ECR 等);
了解分布式训练或多机多卡(DDP / FSDP);
熟悉 Python,具备一定 C++ 或系统工程能力。
加分项
有多模态模型(如 CLIP、LLaVA、Gemini 类)经验;
有云端大规模训练或推理优化经验;
熟悉模型压缩(量化、蒸馏、剪枝);
有边缘端/本地小模型部署经验;
熟悉 AWS 生产级 MLOps 架构;
有 K8s / Docker / CI-CD 实践经验。
Other offers great for you!
These companies are also looking for great profiles
Confidentiel
Assistant Administratif Formation (freelance, confidentielle)
Freelance
Paris, France
Onsite, Hybrid
Skills
13 hours ago
Quick apply
Yunik
Tech Lead IA Agentique / RAG – Azure & Python
Freelance
Paris, France
Hybrid
Skills
8 hours ago
Quick apply
Groupbees
Pilote de projet Data - Niort
Freelance
79000 Niort, France
Onsite, Hybrid
Skills
3 hours ago
Quick apply
No company information available.