Subhajit Bhar

LLM Engineer — Intelligent Document Processing

If your team is manually copying data from PDFs, lab reports, invoices, or document attachments into spreadsheets — that’s an engineering problem. I fix it.

I build production-grade document processing pipelines that eliminate that manual work entirely. Real documents, messy layouts, edge cases included — delivered as a complete system your team can use from day one.

Based in Durham, UK. Working with consultancies, operations teams, and logistics businesses across the UK and beyond.

Book a Diagnostic Session ($250 fixed price) → Share your documents → Get a written action plan within 3 days.

Book a Diagnostic Session →

Recent

Certificate of Analysis Data Extraction: A Production Guide

12 March 2026·1701 words·8 mins

Intelligent Document Processing

A certificate of analysis (CoA) is one of the most information-dense documents in regulated industries. It carries test results, method references, accreditation details, chain-of-custody information, and the laboratory’s sign-off — all in a format designed for human reading, not machine parsing.

Contract Data Extraction: Pulling Structured Data from Legal Documents

12 March 2026·1710 words·9 mins

Intelligent Document Processing

Contracts are the hardest document type to extract data from reliably. Invoices have a predictable structure. Lab reports have defined fields. Contracts are natural language documents, and the information you need — key dates, party names, payment terms, renewal clauses, termination conditions — can appear anywhere, phrased in many different ways, across documents that range from two pages to two hundred.