Tasks:
- * Align model accuracy after quantization
- * Collaborate with hardware, engineering, and testing teams
- * Compress large and multimodal models
- * Design and deploy PTQ and QAT quantization
- * Evaluate quantized model accuracy and validate regressions
- * Integrate optimized models with robot perception, decision, and control systems
- * Optimize inference efficiency on resource-constrained systems
Perks/Benefits:
Skills/Tech stack required:
[Accuracy evaluation] [Action models] [C++] [CUDA] [Deep learning] [Inference Optimization] [Language Models] [Large Language Models] [Linux] [Machine Learning] [Model Compression] [Model Quantization] [ONNX] [Performance Profiling] [PTQ] [Python] [PyTorch] [QAT] [TensorRT] [TVM] [Vision-language] [Vision-language-action] [Vision-Language-Action Models] [Vision Language Models]
Educational requirements:
[Bachelor's Degree]
Role(s):
[AI Systems Engineer] [Deep Learning Engineer] [Embodied AI Systems Engineer] [Engineer] [Learning Engineer] [Machine Learning Engineer] [Systems Engineer]