Senior Research Scientist (Architectures Research)
Nebius
3 weeks ago
Not specifiedmodel architecture researchlong-context modelingattention mechanisms
3 weeks ago
Workplace
Not specified
Posted
3 weeks ago
Summary
Senior Research Scientist at Nebius developing model architectures and methods for competitive open-source AI. The work focuses on attention, long-context memory, reasoning, and reducing training or inference costs.
Responsibilities
- Formulate research questions and design experiments
- Evaluate architectural changes at meaningful model scales
- Develop methods to reduce training and inference costs
- Collaborate on efficient implementations of research ideas
- Publish research and contribute to open-source tools
- Mentor researchers and shape research direction
pythontransformerssparse attentionlinear attentionmodel distillationdistributed trainingefficient inferencelong-context modelingmemory systems
model architecture researchlong-context modelingattention mechanismspersistent memorymodel reasoningefficient inference
