算法工程师/算法工程专家（模型推理平台）-国际支付
Core
Design, develop, and optimize a unified model inference platform for international payment scenarios to support high availability and low latency for large and small models.
Role type
Senior IC Machine Learning Infrastructure Engineer (Inference Platform)
Builds
Unified model inference platform serving risk control and compliance systems in international payments
Domain
Fintech / International Payments / ML Infrastructure
Deliverable
production ML models
Required skills
Model inference optimization, multi-framework deployment (PyTorch/TensorFlow/ONNX), inference scheduling, performance tuning, distributed inference, CI/CD for ML, API gateway design
Preferred skills
LLM inference platform experience, payment/finance high-concurrency deployment, distributed inference (tensor/pipeline parallelism), microservices architecture, gRPC/HTTP API design
Technologies
PyTorch, TensorFlow, ONNX, TensorRT, vLLM, TGI, TensorRT-LLM, DeepSpeed, ONNX Runtime, Golang, Python, C++
