<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/861d222a5c6c42eebe974e151d40e96a&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/861d222a5c6c42eebe974e151d40e96a-dbb1230526bd9192.gif</thumbnail_url><duration>174.263</duration><title>AI Talent Scouting and Outreach Automation 🚀</title><description>In this Loom, I share my AI powered talent scouting and engagement agent built in Streamlit. The main problem I address is not only matching candidates to the job requirements but also identifying candidates who are actually interested, using two scores, match score and interest score. For a sample machine learning engineer role with Python, SQL, PyTorch, 2 to 4 years, and remote India, the system extracts the required skills and generates a ranked shortlist with explanations. I also personalize outreach subject and messages per candidate and combine final score as 0.65 times match score plus 0.3 times interest score. No action is specifically requested from viewers.</description></oembed>