Tutorials & Tips

Job Searcher

Original title:Job Searcher

AI summary

Hugging Face released Job Searcher, an AI-based job search tool. After users upload a resume and set preferences, the system uses teacher model DeepSeek V4 Pro to generate LinkedIn search queries, scrapes jobs via JobSpy, then LoRA-fine-tunes student model Qwen3-8B (8B parameters) to score and reason about each job across five dimensions: skill match, experience relevance, educational background, industry fit and seniority alignment. Training was completed on a single A100 on the Modal platform. Inference is deployed on a Hugging Face ZeroGPU Space, using llama.cpp for streaming output. The project is open-source.

Key Takeaways

  • Hugging Face released Job Searcher,an AI-based job search tool.
  • After users upload a resume and set preferences,the system uses teacher model DeepSeek V4 Pro to…
  • Training was completed on a single A100 on the Modal platform.
  • Inference is deployed on a Hugging Face ZeroGPU Space,using llama.
  • cpp for streaming output.

Quick Facts

Published
Updated
Source
Hugging Face 社区博客(混合发现)
Category
Tutorials & Tips
AI score
65
Read the original Read the full article at the original source
Why it matters

这个 hackathon 项目把教师蒸馏和 LoRA 微调 8B 模型的流程全部开源在 HF 上,做模型定制和部署的开发者能直接抄作业,尤其是推理部署踩的坑(ZeroGPU 上下文重用)很实用。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Job Searcher. June 6, 2026. https://new.nat6.net/en/news/cmq2j2aqq0111slbv2442dsoa/

View all →