Zhenyang Tang

Running Lab

← Back to labs

Job Radar

A daily job intelligence system that scans company career pages, ranks fresh roles against candidate profiles, and sends automated email reports.

In a recent run, it checked 112 company sources, evaluated 14,977 roles, and surfaced 6 new recommendations from 530 score-matching jobs.

Problem

Job boards are noisy, stale, and poorly personalized. The most valuable opportunities are often the newest roles that closely match a candidate’s real background.

Approach

  • Crawl company career pages daily
  • Normalize job data across sources
  • Score roles against multiple candidate profiles

System shape

Daily job intelligence pipeline Crawl once, normalize early, reuse records
Company career pagesPipeline stage
crawler adaptersPipeline stage
normalized job recordsPipeline stage
candidate profile scoringPipeline stage
ranked opportunitiesPipeline stage

Delivery surfaces

markdown report email digest future dashboard

Crawling, normalization, scoring, and delivery stay separate so email reports can ship now while a dashboard can reuse the same scored records later.

Sample daily report

Job Radar Daily Report

Generated May 29, 2026

Pipeline summary

112

Companies checked

14,977

Roles evaluated

530

Score-matching jobs

6

New recommendations

Markdown is used as a portable output format, so the same report can be read in email, saved for history, or later rendered inside a dashboard.

Initial profiles

Frontend Systems / Product UIAI Platform / InfrastructureAI Agent / Agent SDKFull-stack / AI ApplicationsDeveloper Experience / Internal Tools

Status

Running internally: crawls roles, generates ranked markdown reports, and sends automated email digests.

Next

  • Dashboard view for ranked roles
  • Profile selector
  • Explainable scoring breakdowns