ML Optimization Engineer – Training & Inference

Generalist AI; Boston (MA); In loco; USD 150.000 - 230.000; Tempo pieno

Descrizione del lavoro

Generalist AI is hiring a specialist to optimize training and inference on GPUs for cutting-edge embodied AI systems. You will drive step-function gains by refining ML software, hardware interfaces, and kernel-level implementations for transformers and diffusion architectures.

The role focuses on accelerating both training and inference pipelines across the stack, from CUDA kernels to high-levelML frameworks, to deliver scalable, robust performance in real-world robotics contexts.

Competenze

• Experience optimizing ML training and inference on GPUs.
• Familiarity with CUDA kernels and ML architectures.
• Strong performance tuning across CPUs, interconnects, and software stacks.

Mansioni

• Make GPUs go brrrrr.
• Implement ML, hardware, and software changes that lead to step-function gains.
• Optimizing both the inference and training stacks.

Conoscenze

Transformer optimization

Diffusion models

CUDA kernels

PyTorch

NumPy

Python performance

Descrizione del lavoro

Generalist AI is hiring a specialist to optimize training and inference on GPUs for cutting-edge embodied AI systems. You will drive step-function gains by refining ML software, hardware interfaces, and kernel-level implementations for transformers and diffusion architectures.

The role focuses on accelerating both training and inference pipelines across the stack, from CUDA kernels to high-levelML frameworks, to deliver scalable, robust performance in real-world robotics contexts.