N
Senior Deep Learning Researcher
Not specifiedFull-timeAI & Machine LearningComputer Hardware Manufacturing
Conduct advanced research on large language model inference and develop practical algorithms and software that improve latency, throughput, and efficiency on high-performance GPU hardware.
Responsibilities
- Research, design, and implement advanced algorithms for low-latency and high-throughput LLM inference.
- Translate research results into practical software that improves products and customer solutions.
- Collaborate with research, engineering, and product teams internationally.
- Evaluate algorithm performance on current GPU hardware and identify bottlenecks and optimization opportunities.
- Work with scientific organizations and industry experts to incorporate new advances into practical inference technologies.
Requirements
- MSc or PhD in Computer Science, Electrical Engineering, or a closely related field.
- At least 5 years of relevant deep learning or applied research experience.
- Publications at leading AI or machine learning conferences such as NeurIPS, ICLR, or ICML.
- Strong knowledge of LLM architectures and hands-on experience training large-scale models.
- Excellent Python programming skills and experience with deep learning frameworks such as PyTorch.
- Experience applying software engineering standards to research implementations.
Nice to have
- Experience with LLM inference optimization methods such as speculative decoding or parallelization.
- Experience with high-performance computing environments and large-scale GPU clusters.
- Familiarity with LLM inference systems such as vLLM or TensorRT-LLM.
- Research experience at a leading industrial research group or top-tier institution.