N
Senior Deep Learning Research Engineer
В офисеПолная занятостьAI & Machine LearningComputer Hardware
Join a leading hardware technology company to advance the state of the art in Large Language Model inference. You will research, prototype, and optimize algorithms that make LLMs more efficient and scalable on cutting-edge GPU hardware, directly impacting products used worldwide.
Обязанности
- Develop and improve benchmarks, profiling workflows, and evaluation pipelines for inference performance.
- Design and lead experimental frameworks for reproducible evaluation of algorithmic tradeoffs.
- Prototype new LLM inference algorithms for low-latency and high-throughput scenarios.
- Profile algorithm performance on latest GPU hardware to identify optimization opportunities.
- Collaborate with global research, engineering, and product teams on advanced inference technologies.
- Stay current with LLM inference research and translate advances into practical solutions.
Требования
- MSc in Computer Science, Electrical Engineering, or related field, or equivalent industrial research experience.
- At least 5 years of experience in applied research, research engineering, or algorithm engineering.
- Excellent software engineering skills in Python and deep learning frameworks like PyTorch.
- Proven experience with High-Performance Computing environments and large-scale GPU clusters.
- Interest in systems aspects of deep learning: inference engines, benchmarking, profiling, GPU efficiency.
Будет плюсом
- Publication in a top-tier AI/ML conference (e.g., NeurIPS, ICLR, ICML).
- Deep understanding of LLM architectures and hands-on large-scale model training.
- Research experience in LLM inference optimization (e.g., speculative decoding, parallelization).
- Familiarity with LLM inference frameworks such as vLLM or TensorRT-LLM.