Python Engineer – Document Intelligence & RAG

In this role, you will build systems that transform technical documentation into structured knowledge used in diagnostic processes. This position is a unique blend of software engineering, text processing, and LLM-based solutions.

Key Responsibilities:

• Building solutions for analyzing and processing technical documentation.

• Implementing systems based on Retrieval-Augmented Generation (RAG).

• Creating pipelines for document parsing, information extraction, and data structuring.

• Converting unstructured content into clean, readable formats (e.g., JSON).

• Integrating large language models into backend workflows.

• Iteratively improving the quality and accuracy of generated outputs.

Requirements:

• Minimum of 3 years of experience in Python, specifically in data-related tasks or automation.

• Practical experience with LLMs or RAG systems.

• Ability to work with various text formats (PDF, DOCX, HTML).

• Understanding of text data quality issues and NLP (Natural Language Processing).

• Ability to critically evaluate model-generated results.

Nice to Have:

• Experience with tools like FAISS or Pinecone.

• Familiarity with LangChain or LlamaIndex.

• Experience working with engineering or technical documentation.