推理服务框架研发工程师 - Data AML
Core
Designing and implementing high-performance, scalable inference frameworks for large-parameter AI models to support recommendation, advertising, CV, voice, and NLP systems.
Role type
Senior IC inference framework engineer
Builds
Enterprise-grade inference systems for internal business units and external clients via Volcano Engine
Domain
Machine Learning Infrastructure / Distributed Systems
Deliverable
production ML models
Required skills
C/C++ programming, Linux, multi-threading concurrency, distributed service architecture, performance tuning, system design
Preferred skills
Redis, RocksDB, bRPC, gRPC, GPU runtime mechanisms, GPU resource management
Technologies
C++, Linux, gRPC, bRPC, Redis, RocksDB, GPU
Responsibilities
Design overall inference service architecture for large-scale AI models; Develop and optimize inference framework modules including scheduling, monitoring, and gray release; Follow industry trends to select and innovate on inference technologies for distributed high-concurrency scenarios.
