✨ About The Role
- The role involves implementing GPU kernels to adapt models for low precision inference.
- The engineer will write custom load balancing algorithms to optimize serving.
- Profiling and optimizing machine learning tasks and code will be a key responsibility.
- The position requires collaboration on projects that intersect research and product development.
- The engineer will support research through the construction of ML pipelines and reusable code.
âš¡ Requirements
- A successful candidate will have a BSc or MSc in Computer Science or equivalent industry experience.
- The individual should be passionate about solving problems and building innovative solutions.
- Experience in collaborating with AI researchers to implement generative AI features is essential.
- The candidate should have a strong understanding of machine learning tasks and optimization techniques.
- Proficiency in writing efficient code for machine learning tasks is crucial for this role.