Tasks:
- * Build GPU clusters and AI inference infrastructure
- * Deploy and launch large language models
- * Improve GPU utilization
- * Improve service reliability and stability
- * Load-test models and support production launches
- * Monitor production services
- * Optimize LLM inference performance and throughput
- * Optimize model quantization and GPU memory usage
- * Reduce inference costs
- * Troubleshoot production incidents
Perks/Benefits:
Skills/Tech stack required:
[AI infrastructure] [Automation] [Docker] [GPU Acceleration] [GPU clusters] [GPU memory] [GPU Memory Optimization] [Inference Optimization] [Kubernetes] [Linux] [LLM Inference] [Lmdeploy] [Load Testing] [Memory Optimization] [Model Quantization] [Production Monitoring] [Python] [SGLang] [Shell] [TensorRT-LLM] [Transformer] [VLLM]
Educational requirements:
[Bachelor's Degree]
Role(s):
[AI Infrastructure Engineer] [Engineer] [Inference Engineer] [Infrastructure Engineer] [LLM Inference Engineer]