ML Optimization Engineer: Training & Inference for Robotics

Generalist; Medford Hillside (MA); In loco; USD 180.000 - 240.000; Tempo pieno

Descrizione del lavoro

Generalist is seeking a skilled ML optimization engineer to advance the training and on-robot inference stacks. You will focus on making GPUs go faster, implementing ML, hardware, and software changes that drive step-function improvements, and pushing optimization across the entire inference and training pipeline.

The role demands keeping current with the latest ML techniques for transformer and diffusion-based architectures, and diagnosing bottlenecks from CUDA kernels to Python implementations.

Competenze

• Experience optimizing ML training and inference pipelines.
• Strong understanding of transformer and diffusion-based architectures.
• Proficiency with GPU/CPU bottlenecks and parallel computing.

Mansioni

• Make GPUs perform at peak to maximize throughput.
• Implement ML, hardware, and software changes that yield step-function gains.
• Optimize both inference and training stacks for efficiency and speed.

Conoscenze

ML optimization

CUDA kernels

Python PyTorch

Strumenti

CUDA

PyTorch

Descrizione del lavoro

Generalist is seeking a skilled ML optimization engineer to advance the training and on-robot inference stacks. You will focus on making GPUs go faster, implementing ML, hardware, and software changes that drive step-function improvements, and pushing optimization across the entire inference and training pipeline.

The role demands keeping current with the latest ML techniques for transformer and diffusion-based architectures, and diagnosing bottlenecks from CUDA kernels to Python implementations.