公有云机器学习系统工程师-推理方向
Core
Design and develop machine learning inference architecture and products for the VolcEngine Ark large model platform and machine learning platform.
Role type
Senior IC machine learning systems engineer (inference)
Builds
Stable, observable, high-concurrency, high-throughput public cloud inference platforms supporting multi-tenant environments.
Domain
Cloud computing + Machine Learning Infrastructure
Deliverable
production ML models
Required skills
Go/Java/Python, Linux, data structures and algorithms, TensorFlow/PyTorch, Kubernetes, distributed systems design, online service governance, deployment architecture
Preferred skills
Online GPU inference optimization (Batch, quantization, distributed inference), CUDA, RDMA, AI Infrastructure, HW/SW Co-Design, High Performance Computing, ML Hardware Architecture, Distributed Storage
Responsibilities
Design and optimize online inference architectures utilizing heterogeneous compute (GPU, CPU), storage, and network resources; build stability and observability systems for multi-tenant environments; productize inference systems to ensure first-class user experience.
