Senior JavaFX Engineer (AI Invoice Reader → CSV)

JavaFX

• 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

• 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

• 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

Java 17+, JavaFX, Gradle

• ≥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

• 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