Machine Learning Engineer
Current• Optimize inference on large language models (LLM) after throughput analysis,increasing inference speed by 10x and annotation throughput by 2x to reach quarterly goal.• Led a data annotation team of 5 by implementing streamlined processes after optimizing LLM inference, doubling the number of labels in existing system.• Developed a product search engine by implementing a semantic searchpipeline with vector database, increasing absolute search precision by 29% in offline retrieval tests.