About this role
Join AI Singapore hosted at NTU as an AI Engineer on the Platform team to design and implement optimized LLM inference workflows, operate the SEA-LION multi‑cloud LLM inference platform, and manage GPU-enabled AI clusters, CI/CD, observability, and deployment automation to serve LLMs in production.
Skills for this role
Large Language Models (LLMs)Retrieval-augmented generation (RAG)AI agent orchestrationGPU-enabled AI infrastructureMulti-cloud deploymentvLLMSGLangTensorRT-LLMTransformersModel servingGPU schedulingAutoscalingLatency optimisationThroughput optimisationInference cost managementInfrastructure as CodeTerraformDockerKubernetesCI/CDContainer registriesDeployment automationObservabilityLogsMetricsTracesREST API designModel Context Protocol (MCP)OAuthIncident response」「Python""Bash""Claude""Copilot""Cursor""Multimodal AI""C