I got tired of losing good jobs to timing, so I built a pipeline that scores LinkedIn listings against my CV and emails me the best matches
A job posting gets 200+ applicants in 48 hours. By the time LinkedIn's daily digest hits your inbox, the window is already closing. I kept finding great matches days after they were posted. So I built SnapplAI: it scrapes fresh LinkedIn listings, sends each one to Gemini to score it against your CV, and emails you only the top matches, before the crowd even sees them. How it works Four steps, one…
SnapplAI is a job hunting tool that automatically identifies the most suitable job postings for a user's CV. Instead of waiting for the daily LinkedIn digest, which often contains listings that have already passed their deadline, SnapplAI offers a solution that proactively scores new listings against the user's CV and emails the best matches directly to the user's inbox.
The tool is built using four simple steps: scraping fresh LinkedIn listings based on user-defined filters, summarizing each listing through Gemini's AI to extract structured fields, scoring each job against the user's CV using chain-of-thought reasoning, and emailing the top matches to the user's inbox. The entire process runs locally, via Docker, or as a scheduled GitHub Actions cron job, and can be set up in just five minutes.
One of the key benefits of SnapplAI is its simplicity. The developer chose to build a clean data pipeline with explicit LLM calls, rather than using an agent framework. Python is used to orchestrate the data flow, while AI is used to evaluate the job matches. Furthermore, the tool includes robust error handling with exponential backoff retries and model chaining to ensure that API throttling does not disrupt the workflow.
SnapplAI is licensed under the MIT license and welcomes contributions in the form of issues, pull requests, and forks.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
