Data & ML Engineer

Overview

The Data & ML Engineer will focus on document ingestion and retrieval-augmented generation (RAG) for an AI company serving government and defense sectors. This contract role involves transforming unstructured data from various documents into structured content that can be utilized in production pipelines. Working collaboratively within a team, the engineer will scale proven prototypes into robust, production-ready systems.

Responsibilities

  • Pull clean, structured text from messy PDFs, Word documents, and HTML files.
  • Transform document contents for integration into RAG pipelines.
  • Scale working prototypes into production systems.
  • Implement document parsing techniques for various formats including tables and multi-column layouts.
  • Utilize technologies such as Unstructured, Docling, PyMuPDF, and OCR for document ingestion.
  • Develop and maintain production-level code using Python, FastAPI, and CI/CD practices.
  • Conduct testing with PyTest and containerization using Docker.

Requirements

  • Proven background in data or software engineering, increasingly focused on machine learning and RAG methodologies.
  • Hands-on experience with document parsing, including handling tables and multi-column layouts.
  • Familiarity with unstructured document processing tools like Unstructured, Docling, and PyMuPDF.
  • Experience with retrieval-augmented generation techniques involving chunking, embeddings, and vector search, especially using Postgres and pgvector.
  • Proficiency in Python with experience in frameworks such as FastAPI.
  • Understanding of CI/CD pipelines and testing practices, including Docker and PyTest.
  • Must demonstrate prior work on document ingestion projects.
OIR35+ members get up to 3 days early access to new jobs
SkillsMachine Learning, RAG, CI/CD
TechnologiesHTML, PostgreSQL, Python, FastAPI, Docker
LocationLondon Area
TypeOn-site
Rate
£600-£700/day
PostedNEW