火山方舟服务端研发（平台方向）-火山方舟
Core
Manage the full lifecycle of Large Language Models (LLM) from introduction and evaluation to fine-tuning, deployment, and monitoring; build high-performance inference services and multi-tenant platform capabilities.
Role type
Senior IC backend engineer (LLM platform & inference)
Builds
Model repository systems, high-performance inference services, and multi-tenant platform infrastructure
Domain
AI/ML infrastructure, distributed systems, cloud platforms
Deliverable
production ML models
Required skills
Golang/Java/C++/Python, distributed systems, microservices architecture, high-concurrency systems, caching, message queues, load balancing, system design
Preferred skills
Model fine-tuning, model quantization, multi-region data synchronization, resource isolation
Technologies
LLM frameworks, distributed computing frameworks, container orchestration
Responsibilities
Build and maintain model versioning and asset management systems; optimize inference services for speed and efficiency; implement multi-tenant resource isolation and quota management; collaborate with algorithm and product teams to deploy models in business scenarios.