Inference Performance Engineer - MaaS
Bitdeer
PythonSQLLLMGrafanaPrometheusSparkpandasGPUInferenceSGLangTensorRT-LLMTriton
Описание
Bitdeer is looking for an Inference Performance Engineer to characterize production workloads and improve capacity, cost, and performance metrics.
Requirements
- SQL
- LLM
- Spark
- GPU
- Capacity planning
- Grafana
- Triton
- Prometheus
- Inference
- Pandas
- TensorRT-LLM
- SGLang
- Python
- vLLM
- Tracing
- Performance engineering