Freelance Senior Javafx Engineer

The missionBuild 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 buildJavaFX 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 have4+ 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 havePrompt 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 < 60 seconds One-click CSV export that matches our schema and loads cleanly What we provideLabeled 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