Backend Engineer - ARK Large Model Platform (Singapore)
Core
Develop and optimize the ARK Large Model Platform on Volcano Engine to reduce IT costs for large model applications across various industries.
Role type
Senior Backend Engineer (Large Model Infrastructure)
Builds
Cloud-native machine learning platform products, high-performance model inference services, and systematic solutions for large model implementation.
Domain
AI Infrastructure / Cloud Computing / Large Language Models
Deliverable
production ML models | infrastructure
Required skills
Distributed systems design, Golang/Python/C++/Java/Scala, Kubernetes/Operator development, Microservices & Service Mesh, Model training & inference optimization, RLHF/Dataset construction, Terraform, Cloud storage management
Preferred skills
ACM ICPC/Codeforces experience, Prompt engineering, Retrieval Augmented Generation (RAG), LangChain, New model exploration (LLaMA, Falcon)
Technologies
Volcano Engine, Kubernetes, Terraform, Linux, Golang, Python, C++, Java, Scala, Javascript, LLaMA, Falcon, miniGPT4
Responsibilities
Research systematic solutions for large model implementations, design and develop specialized utility programs for ML platforms, integrate hardware and software systems, update and enhance existing software capabilities
Seniority
Senior, hands-on IC