Profile cover
E

AI Intelligent Table Extraction Developer

Nortex Solutions

Remote · $130k – $160k / year · Full-time · Posted 4 months ago

No longer accepting applications

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Tables inside PDF documents are the bane of document processing. Financial statements with merged cells. Medical forms with spanning headers. Regulatory filings where the table continues across three pages with subtly different column layouts. Standard PDF parsers produce garbage on these. OCR produces boxes of text with no structure. Our clients need the actual tabular data with its semantic structure intact. We've already solved flat, simple table extraction. The hard cases remain: tables with hierarchical headers, tables nested inside other tables, tables that use color and shading to encode meaning that disappears in greyscale OCR, and tables where row/column structure is implied by layout but not explicit in the PDF structure. As a senior engineer, you'll build the advanced table extraction system that handles these cases. The approach combines layout analysis, computer vision for structure inference, and LLM post-processing for semantic validation. You'll design the model pipeline, build the confidence scoring that routes difficult cases for human review, and create the evaluation benchmark suite that tracks accuracy across our corpus of hard table types. Production accuracy target: 93% cell-level F1 on the hard case benchmark.

Fully remote.

Responsibilities

  • Design advanced table extraction pipeline combining layout analysis, vision, and LLM post-processing
  • Build structure inference for tables with hierarchical headers, merged cells, and cross-page continuations
  • Implement confidence scoring routing difficult extractions for human review
  • Create evaluation benchmark suite covering the identified hard table type corpus
  • Develop cell-level accuracy metrics tracking extraction quality across table categories
  • Integrate extraction pipeline into the existing document processing workflow APIs

Requirements

  • 6+ years in document processing, computer vision, or NLP engineering
  • Experience building production PDF or document extraction systems
  • Strong Python and PyTorch skills with layout understanding model familiarity
  • Hands-on experience with LLM-assisted document understanding approaches
  • Track record shipping extraction systems with rigorously measured accuracy

Benefits

  • Fully remote with flexible schedule
  • Comprehensive health benefits
  • $4,000 annual professional development budget
  • Equity participation
  • Performance bonus

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

Automation & AI Workflows AI Business, Marketing & Strategy

Skills

python pytorch openai api fastapi docker

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Materials Lead

Lambda

Full-time Lead

Sr. Solutions Architect - Travel and Hospitality

Databricks

Full-time Senior

AI Researcher - Pre-training (f/m/d)

Aleph Alpha

Full-time

Research Engineer / Scientist, Pre-training

Anthropic

Full-time

Revenue Operations Manager

Handshake

Full-time

AI Security Engineer Intern (Summer 2027)

Brainco

Full-time Intern

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$130k – $160k / year

AI Expertise

Automation & AI Workflows AI Business, Marketing & Strategy

Skills

python pytorch openai api fastapi docker sql

Ready to apply for this role?

Create a free talent account.

  • Find AI roles in one place
  • Get AI-matched job recommendations
  • Reply to companies that message you
  • Build your public AI talent profile
Create free account & apply Log in

This role is closed. Create your free profile to apply to similar open roles.

Don't miss the next one: get matched to new roles like this.

Create free profile