%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
LinkedIn has recently launched its new AI-powered network search feature, marking an important step for the company in the field of generative artificial intelligence. Although the launch of this feature has been long-awaited, it is the result of the engineering team's persistent efforts in technical optimization and practicality. This new feature allows users to find relevant professionals through natural language queries, such as "Who has knowledge about cancer treatment?" instead of being limited to traditional keyword searches.
Different from previous keyword-based search methods, the new system can understand the user's search intent, grasp semantic relationships, and automatically recommend related experts and researchers. For example, even if a professional's profile does not mention "cancer," the system can identify connections with "oncology" or "genomic research" and provide more accurate recommendations. At the same time, the system also considers the user's social network relationships when recommending results, ensuring that users can more easily connect with relevant experts.
To achieve this intelligent search, the LinkedIn team developed an efficient technical framework called "Recipe." Through this framework, they tested large amounts of data on a small scale and successfully distilled the core model. After continuous optimization, the team finally reduced the model parameters from 440M to 220M, significantly improving processing speed and enabling the system to efficiently serve 1.3 billion users.
In terms of infrastructure, LinkedIn also made significant changes, moving the retrieval system from a CPU-based architecture to a GPU architecture to handle large volumes of data and faster response requirements. In addition, the team created a new intelligent query routing layer that selects the best search method based on the characteristics of the user's query.
LinkedIn's upgrade not only enhances the user experience but also provides a reference for other companies building artificial intelligence systems, emphasizing the importance of gradual optimization and teamwork.
Key points:
📌 LinkedIn launches AI-powered network search, allowing users to find relevant experts through natural language queries.
🔍 The new system understands search intent and can identify professionals in related fields, providing more accurate results.
⚙️ The team developed an efficient technical framework, reduced model parameters to improve processing speed, and optimized the user experience.