Overview
The Generative AI Engineer will contribute to advanced on-device AI technology by porting and optimizing inference engines for efficient operation on edge hardware. Working closely with researchers, the role emphasizes the transition of models into production-ready deployments and the integration of AI capabilities into current products. This fully remote position is suited for candidates in Europe who are passionate about advancing AI technologies.
Responsibilities
- Deploy and optimize machine learning models to edge devices using industry-standard inference frameworks.
- Collaborate with researchers to transition models from research to production-ready deployments.
- Integrate AI capabilities into existing products, ensuring alignment with the latest machine learning advancements.
- Port and optimize inference engines for efficient operation on edge hardware.
Requirements
- Strong programming skills in C++.
- Hands-on experience with open-source inference engines and model deployment.
- Solid understanding of deep learning concepts and model architectures.
- Experience with large language models and transformer-based architectures.
- Ability to quickly learn new technologies.
- Degree in Computer Science, AI, Machine Learning, or a related discipline, with a proven track record in AI R&D.