This job offer is not available in your country.

Senior JavaFX Engineer (AI Invoice Reader → CSV)

Invito Staffing SolutionsIndia, India

17 hours ago

Job description

The mission

Build a desktop JavaFX application that lets non-technical users drop in invoices (PDF / image) and export clean CSV data. Invoices come in all shapes—your job is to make the app read them like a human : robust parsing, confidence scoring, and easy validation.

What you’ll build

JavaFX desktop app (Java 17+) with a clean, responsive UI
Invoice ingestion : PDF, PNG / JPG, multi-page, batches, drag-and-drop
AI / OCR pipeline (choose best fit; hybrid is fine) :
Classical OCR (e.g., Tesseract ) + layout analysis or
Cloud OCR (e.g., AWS Textract , Google Vision ) or
LLM-assisted parsing (prompting / JSON schema) with guardrails
Field extraction (line-items + headers) : vendor, invoice #, dates, currency, taxes, subtotals / totals, PO, line descriptions, qty, unit price, amounts
Validation & review UI : highlight zones, flag low-confidence fields, quick fixes, autocomplete
CSV export : stable schema, locale / number / date normalization
Rules & heuristics : vendor templates, regex fallbacks, learned patterns
Quality metrics : confidence scores, per-field accuracy, reject reasons, simple analytics
Operate offline where possible with optional cloud connectors

You’re a great fit if you have

4+ years Java; 2+ years JavaFX building production desktop apps

Real-world OCR / NLP or document understanding experience (invoices, receipts, forms)

Hands-on with one or more : Tesseract , Textract , Google Vision , Azure Form Recognizer , OpenCV , spaCy , LLM JSON extraction

Comfortable designing parsing pipelines : pre-processing, layout detection, table extraction, post-processing, and human-in-the-loop review

Strong data wrangling : CSV schemas, date / currency parsing, edge cases

Solid testing : golden files, fixture PDFs, deterministic pipelines

Nice to have

Prompt engineering for structured outputs with LLMs

Vendor-specific templateing and auto-learning

Experience with Maven / Gradle , native packaging, code signing

Knowledge of ONNX / TensorFlow Lite models for document layout

Basic DevOps for OCR services and model hosting

Tech we expect to use (flexible)

Java 17+, JavaFX, Gradle , Tesseract / OpenCV or Textract / Vision , optional Python micro-services for ML bits, SQLite for local cache, JUnit + test fixtures, GitHub Actions CI.

Success looks like

≥95% header-field accuracy on a mixed test set

≥90% line-item recall on clear tabular invoices

Review UI fixes a typical invoice in

One-click CSV export that matches our schema and loads cleanly

What we provide

Labeled sample invoices (PDFs / images) across vendors

Target CSV schema + acceptance tests

Design mocks for the core screens

Fast feedback loop with a technical product owner

Create a job alert for this search

Senior Ai Engineer • India, India