Senior Backend Engineer – LLM Extraction

* This requirement is best viewed with a Markdown viewer · # PDF Data Extraction · We need a developer to extract ESG metrics from a PDF report and output **two files per PDF**: · 1. **A structured CSV or JSON** containing the extracted ESG values · 2. **A separate "verification ...

We're dealing with highly differentiated physical products that have complex classification challenges.We need someone who can help us design a robust product taxonomy and implement LLM-based extraction and deduplication to normalize messy real-world data into that structure. · ...

We are looking for an experienced engineer to design and implement a highly scalable solution for extracting structured data from large language model interfaces. · ...

We are seeking an AI data extraction expert to develop a custom LLM model for extracting plan drawing and construction data from PDFs. The model should efficiently process and categorize data, ensuring high accuracy and reliability. · ...

I am looking for a Python developer to implement an extraction pipeline using an LLM API. · ...

We are looking for an experienced developer to build a proof-of-concept using C# console applications that demonstrates an end-to-end Retrieval-Augmented Generation (RAG) workflow. · ...

NDA will be required to move forward. · *ROLE · Python / AI Data Engineer — Web Crawling + LLM Structured Extraction (1,000+ domains, 383-column Excel output) · *ABOUT · We're an early-stage startup building an internal "company intelligence" dataset that powers a comparison prod ...

We're building a feature that uses LLMs as core reasoning components within a data pipeline. · It's a system where LLMs handle classification, extraction, fuzzy matching, and ranking as part of a larger workflow. · ...

You will lead the conversion of manual Excel-heavy capital reporting processes into scalable automated Power BI solutions. · Design and deliver end-to-end Power BI dashboards and data models for capital reporting. · ...

We need an experienced RAG developer who can optimize our sentiment analysis system to deliver reliable, high-quality sentiment analysis at scale. · ...

We are building an institutional-grade Agentic Deal Desk that automates real estate underwriting. · Key Technical Requirements include:Production experience with Vision-capable LLMs to parse complex document layouts. · Ability to handle OCR and spatial data extraction from PDFs. ...

I need a developer that is great at scraping/extracting data from a website in an organized manner for the purpose of LLM fine tuning · ...

I am looking for someone who can help me automate the following:Image uploaded of an A4 DocumentDocument is parsed and the required data extractedThe data is put into a Google sheet in a set format. · ...

We're building an AI-driven system that automatically analyzes large document collections discovers content categories generates extraction schemas and stores structured data in PostgreSQL · Automatically classify document content and discover schemas · Generate Pydantic and data ...

We are seeking an experienced Data Engineer & Web Crawling Expert to build a modern scalable data collection system. · - Develop custom scrapers using Crawl4AI to extract structured data (JSON/Markdown) optimized for LLMs. · - Implement advanced extraction strategies (Pydantic s ...

A reusable knowledge extraction tool for PDFs and books that enforces coverage checks, evidence traceability, and passes validation across five texts. · ...

We are looking for a high level Machine Learning Engineer with specific experience in Intelligent Document Processing (IDP) to help us transition from a zero-shot OCR+LLM approach to a robust fine-tuned production system targeting 95% accuracy. · We process thousands of Bank Stat ...

+Job summary · We are seeking an experienced ML Pipeline Engineer to design and scale LLM-powered pipelines that streamline investment research. · +Architect end-to-end LLM pipelines for ingestion, intelligent chunking, RAG retrieval, structured extraction, multi-label classifica ...

We are building a B2B SaaS web platform to automate the retrieval and intelligent processing of specific documents from several property management extranets. · ...

We are building a production-grade search system that extracts structured signals from unstructured CV text and generates precise OpenSearch DSL queries to return experts with clear explanations. · Prompt engineering ownership: Design high-quality prompts for schema-constrained e ...