<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/job-searcher-jnnq5luqj" -->

---
title: Job Searcher | daily.dev
description: A fine-tuned job search assistant built on Qwen3-8B using knowledge distillation from DeepSeek V4 Pro. The system takes a resume and preferences, generates...
canonical: https://daily.dev/posts/job-searcher-jnnq5luqj
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Job Searcher | daily.dev
og:description: A fine-tuned job search assistant built on Qwen3-8B using knowledge distillation from DeepSeek V4 Pro. The system takes a resume and preferences, generates...
og:url: https://daily.dev/posts/job-searcher-jnnq5luqj
og:image: https://api.daily.dev/og/posts/jNnQ5LuQJ.png
og:image:alt: Job Searcher
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Job Searcher

**[Hugging Face](https://daily.dev/sources/huggingface)** · 4 min read · 19 upvotes · 1 comments

## Summary

A fine-tuned job search assistant built on Qwen3-8B using knowledge distillation from DeepSeek V4 Pro. The system takes a resume and preferences, generates LinkedIn search queries via JobSpy, then scores each job posting across five dimensions (skills match, experience relevance, education, domain fit, seniority alignment). Training used two separate LoRA SFT adapters — one for query generation, one for fit evaluation — trained on 2,500 resumes and ~10,000 scraped job postings labeled by the teacher model. Inference runs via llama.cpp on HuggingFace ZeroGPU Spaces with streaming output. Key lessons: splitting tasks into two adapters eliminated formatting leakage, and the quality of the teacher's labeling prompt had more impact than student model size.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://huggingface.co/blog/build-small-hackathon/job-search-blog>

## Similar posts on daily.dev

- [How LinkedIn Trains AI Job Search 8x Faster with Multi-Teacher Distillation](https://daily.dev/posts/how-linkedin-trains-ai-job-search-8x-faster-with-multi-teacher-distillation-ero71wxem) · InfoQ · 1 upvotes · 0 comments
- [Reimagining LinkedIn’s search tech stack](https://daily.dev/posts/reimagining-linkedin-s-search-tech-stack-mwajgbtsf) · LinkedIn Engineering · 1 upvotes · 0 comments

---

Tags: [#qwen](https://daily.dev/tags/qwen), [#lora](https://daily.dev/tags/lora)

[View this post on daily.dev](https://daily.dev/posts/job-searcher-jnnq5luqj)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Job Searcher","url":"https://daily.dev/posts/job-searcher-jnnq5luqj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/job-searcher-jnnq5luqj"},"datePublished":"2026-06-06T15:38:57.992Z","dateModified":"2026-06-06T15:39:19.929Z","description":"A fine-tuned job search assistant built on Qwen3-8B using knowledge distillation from DeepSeek V4 Pro. The system takes a resume and preferences, generates...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d00b61fa291a2bb679e2dfed291cce2c?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d00b61fa291a2bb679e2dfed291cce2c?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hugging Face","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hugging Face","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f1f55c67d81a4330acf5b90b26b0c8e1","url":"https://daily.dev/sources/huggingface"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/job-searcher-jnnq5luqj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":19},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"qwen,lora","timeRequired":"PT4M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hugging Face","item":"https://daily.dev/sources/huggingface"},{"@type":"ListItem","position":3,"name":"Job Searcher"}]}
```

