火山方舟服务端研发（平台方向）-Data AML
Core
Manage the full lifecycle of Large Language Models (LLM) from introduction and evaluation to fine-tuning, deployment, and monitoring; build and maintain model repositories for versioning, asset management, and traceability.
Role type
Senior IC backend engineer (LLM platform & inference)
Builds
High-performance LLM inference services, model repositories, and multi-tenant platform capabilities
Domain
Artificial Intelligence / Large Language Models / Distributed Systems
Deliverable
production ML models
Required skills
LLM lifecycle management, model fine-tuning, distributed system design, microservices architecture, high-concurrency system development, model quantization, distributed inference, multi-region data synchronization, multi-tenant resource isolation, permission control, quota management
Preferred skills
System design and abstraction, caching, message queues, load balancing
Technologies
Golang, Java, C++, Python
Responsibilities
Build and maintain model warehouse systems for version management and asset tracking; Develop high-performance inference services with optimization and acceleration; Implement multi-region model and metadata synchronization; Construct multi-tenant capabilities including resource isolation and access control; Collaborate with algorithm, data, and product teams to deploy model capabilities in business scenarios.