As a Principal Machine Learning Engineer focused on model optimization algorithms, you will work closely with our product and research teams to develop SOTA deep learning software. You will collaborate with our technical and research teams to develop LLM training and deployment pipelines, implement model compression algorithms, and productize deep learning research. If you are someone who wants to contribute to solving challenging technical problems at the forefront of deep learning in the open source way, this is the role for you.

Contribute to the design, development, and testing of various inference optimization algorithms in the vLLM, and related projects, such as llm-d and LLM-compressor  projects.

Create and manage inference serving deployment pipelines

Benchmark, profile, and evaluate different parallelizations, quantization and sparsification approaches to determine the best performance for specific hardware and models

Participate in technical design discussions and provide innovative solutions to complex problems

Stay up-to-date with the latest advancements in the open source LLM model architecture, LLM Inference parallelizations/optimizations techniques, and quantization research

Stay up-to-date of latest CPU and GPU hardware architecture and features to boost AI inference performance

Give thoughtful and prompt code reviews

Mentor and guide other engineers and foster a culture of continuous learning and innovation

Continuous collaboration with internal and external open source comitters and contributors while contributing to vLLM and related projects