AI Engineer
Develop and deploy AI models on specialized hardware, with a focus on quantization, performance, and accuracy. The role involves research into generative AI architectures and development of hardware-aware tools.
Responsibilities
- Explore and plan end-to-end deployment of neural networks on company hardware.
- Own measurement and improvement of network accuracy.
- Develop a hardware-aware quantization tool for the graph compiler.
- Research emerging generative AI architectures and develop expertise in their algorithms.
Requirements
- Bachelor’s or master’s degree in engineering, computer science, or a related technical field.
- 3–4 years of experience as a Python developer.
- Experience with PyTorch and evaluating and running machine learning or AI models.
- Knowledge of common AI model architectures.
- Proficiency with AI tools and sound testing practices.
Nice to have
- Experience with large language models.
- Experience with network quantization methods.
- Experience with Hugging Face, PyTest, or Jenkins.