Quezaal Product

MarketLens

AI-Powered Job Market Intelligence Platform

Automatically collect job postings from LinkedIn, Indeed, and Glassdoor — then let a local large language model extract the intelligence hidden inside: skills in demand, seniority patterns, salary ranges, remote trends, and company hiring signals. All delivered as a live analytics dashboard.

3+Job Boards
LLMAI Enriched
8+Analytics Views
AnyCloud or Local
Request a Demo See Features
🔍

Multi-Source Harvesting

LinkedIn · Indeed · Glassdoor — collected automatically on schedule via Apify

↓ Raw Job Postings · Deduplicated ↓
🧠

Local LLM Enrichment

Llama 3.1 8B via Ollama — extracts skills, seniority, salary, work setting, sponsorship

↓ Structured Intelligence · Stored in Postgres ↓
📊

Live Analytics Dashboard

Skills trends, salary ranges, seniority distribution, company signals — updated every run

↓ Searchable · Filterable · Exportable ↓
🔒

Your Infrastructure

Deploy on your terms — local server, private cloud, or on-premise. Your data never leaves your environment.

500+
Jobs per run
5h
Auto-refresh cycle
15+
Search filters
0
Manual effort after setup
The Problem We Solve

Job Market Intelligence Shouldn't Require a Team of Analysts.

Current State

  • Job market research is manual, time-consuming, and immediately out of date
  • Raw job postings bury the signal — skills, salary, and seniority require reading every post
  • No single view of hiring trends across LinkedIn, Indeed, and Glassdoor simultaneously
  • Cloud AI tools send your competitive research data to external servers
  • Spreadsheets and manual tagging don't scale — and they're always behind
  • Salary benchmarking requires expensive third-party subscriptions

With MarketLens

  • Harvesting runs automatically — new intelligence every 5 hours with zero manual effort
  • Local LLM reads every posting and extracts structured data — skills, seniority, salary, work setting
  • Unified dashboard across all sources — one view of the full market
  • LLM runs entirely on your hardware — your research data stays private
  • Real-time charts update with every pipeline run — always current intelligence
  • Salary min/max extracted by AI from every posting that includes it — free, continuous benchmarking
Core Capabilities

Everything You Need to Understand Your Market, Automatically

01

Automated Multi-Source Collection

MarketLens connects to LinkedIn, Indeed, Glassdoor, and other major job boards through a reliable harvesting layer. Searches are fully configurable — keywords, location, portals, max results, and lookback window. The pipeline runs on a schedule and deduplicates postings automatically, so your database grows cleanly over time.

LinkedIn Indeed Glassdoor Scheduled Pipeline Deduplication
02

Local LLM Intelligence Layer

Every collected job posting passes through a locally-hosted large language model (Llama 3.1 8B via Ollama). The LLM reads the full description and extracts structured fields: required skills, seniority level, salary range, work setting, employment type, role category, development type, and sponsorship requirements. No cloud API needed — the model runs on your hardware.

Llama 3.1 8B Ollama Skills Extraction Salary Parsing Local Processing
03

Real-Time Analytics Dashboard

An always-live dashboard summarises the entire market at a glance: top skills bar chart, role category pie, seniority distribution, salary ranges, timeline of postings per day, top hiring companies, most active locations, remote vs hybrid vs on-site breakdown, and employment type split. Click any chart element to jump to the filtered jobs list instantly.

Skills Trends Salary Benchmarks Seniority Distribution Company Signals Interactive Charts
04

Searchable Jobs Explorer

Browse every collected posting in a sortable, filterable table with 15+ search parameters: keywords, seniority, role category, skill, source, location, date range, salary floor/ceiling, work setting, employment type, and custom flags. Save your filter sets as defaults. Flag individual jobs as starred, applied, rejected, or archived. Right-click any row to act.

15+ Filters Saved Defaults Custom Flags Sort by Any Column Job Detail Panel
Under the Hood

How MarketLens Works

🔍

Harvest

The pipeline pulls job postings from configured portals on schedule. Each run collects up to 500 fresh postings, skipping exact duplicates already in the database.

🧠

Enrich with AI

Each new posting is passed to the local LLM. The model reads the full description and returns structured JSON: skills, seniority, salary, work setting, role category, and more.

📊

Analyse

Enriched data is aggregated into the analytics layer. Dashboard charts, stats cards, and trend lines update automatically — no manual refresh required.

🎯

Act

Search, filter, flag, and drill into the data. Click a chart to filter the jobs table. Open original postings directly. Export via SQL for deeper analysis.

🧠
AI Layer
Ollama · Llama 3.1 8B · Local inference
🗄️
Data Store
PostgreSQL 16 · Redis 7 · Job queue
⚙️
API & Pipeline
FastAPI · Python · Apify harvesting
🐳
Deployment
Local or Cloud · Nginx · Scalable workers
The Intelligence Engine

A Large Language Model That Reads Every Job Posting For You

At the core of MarketLens is a locally-hosted Llama 3.1 8B model running via Ollama. Unlike cloud-based AI services, the model operates entirely within your infrastructure — your job market data never leaves your environment.

The LLM does what would take a human analyst hours per day: it reads the natural language of each posting and produces structured, queryable fields. No rules engines. No regex patterns. No hand-coded taxonomy. The model understands context — it knows that "5+ years with PyTorch" means Senior, that "competitive compensation" needs to be flagged as undisclosed, and that "AWS, Python, and Spark" map to distinct skill categories.

Discuss a Deployment
🔬

Skills Extraction

The LLM identifies every technical and soft skill mentioned in the posting — normalised to a consistent vocabulary so charts aggregate meaningfully across thousands of jobs.

📈

Seniority Classification

Junior · Mid · Senior · Lead · Principal · Executive — classified from context, not just title keywords. The model reads years of experience, scope of responsibility, and reporting structure.

💰

Salary Parsing

Min and max salary extracted from any format the posting uses — hourly, annual, range, or approximate — and normalised to an annual figure for consistent benchmarking.

🏠

Work Setting & Sponsorship

Remote · Hybrid · On-site classified from job description context. Visa sponsorship availability extracted and flagged — critical signal for workforce planning and candidate fit.

Enterprise Ready

Built for Teams, Not Just Analysts

👥

Multi-User Access

User registration with email verification and role-based access control. Admin and standard user roles. Public registration can be disabled after initial team onboarding.

🔐

Two-Factor Authentication

Optional TOTP-based 2FA compatible with Google Authenticator, Authy, Microsoft Authenticator, and any standard TOTP app. Per-user control from the Settings panel.

Scalable Architecture

Deploy on a local server, private cloud (AWS, Azure, GCP), or on-premise infrastructure — all with a single command. Scale workers and API instances independently. Nginx load-balances traffic automatically, supporting multi-server deployments for large teams.

Ready to See Your Market Clearly?

Talk to us about deploying MarketLens for your team or organisation.

Request a Demo See All Products