AI Engineer, Platforms
Core
Design and implement optimized inference workflows and support building customized LLM-based solutions for production deployment.
Role type
Senior IC AI Platform Engineer (LLM Infrastructure)
Builds
Multi-cloud LLM inference platforms, API services, and GPU-enabled AI infrastructure
Domain
Artificial Intelligence / Cloud Infrastructure / Large Language Models
Deliverable
production ML models
Required skills
LLM inference optimization, GPU cluster management, Infrastructure as Code, CI/CD pipeline development, Observability engineering, REST API design, Model Context Protocol (MCP), Python scripting, Cloud provider operations
Preferred skills
Multimodal AI model experience, C/C++/Rust/Go programming, Open-source AI/ML contributions
Technologies
vLLM, SGLang, TensorRT-LLM, Terraform, Docker, Kubernetes, Claude, Copilot, Cursor
Responsibilities
Operate and monitor multi-cloud LLM inference platform (SEA-LION API Farm), optimize LLM inference across modalities, build new API services, manage high-performance AI clusters and storage systems, develop CI/CD pipelines and deployment automation, strengthen observability across the stack
Seniority
Mid-level, hands-on IC
