Graphrag Developer Challenge

Altro; Bolzano; In loco; EUR 30.000 - 50.000; Part-time

Descrizione del lavoro

A tech company in Bolzano is seeking a Senior RAG Systems Developer for a contract role focused on legal document processing. This position involves technical evaluation with a potential for long-term hire, requiring expertise in graph-based retrieval and Python development. The deliverables include implementing functions for knowledge graph construction and parallel query execution, culminating in a live demo. Compensation is $600 upon successful benchmark completion.

Competenze

• Expert in graph-based retrieval required for high-accuracy prototype.
• No UI or API keys provided; stack flexibility allowed.
• Queries must support parallel execution and be performant.

Mansioni

• Build a prototype for legal document reasoning using provided materials.
• Implement two core functions in Python.
• Conduct a live demo showcasing the developed system.

Conoscenze

Graph-based retrieval expertise

Python programming

Knowledge graph construction

Multi-hop reasoning

Strumenti

Python 3.12

Poetry

Descrizione del lavoro

GraphRAG Developer Challenge – Legal Document Processing (Prototype)

Senior RAG Systems Developer (Contract / Freelance)

Compensation

$600 – paid only if you pass (95% benchmark)

Timeline

3–5 days from materials receipt to live demo

Purpose

Technical evaluation for potential long‑term hire

Frontend / UI

None (backend prototype only)

Contact

Contact : Objective

We're seeking an expert in graph-based retrieval (GraphRAG) to build a high‑accuracy prototype for legal document reasoning. This is a paid technical test that may lead to a long‑term position. The goal is a true GraphRAG system featuring explicit knowledge‑graph construction and traversal, multi‑hop reasoning, agentic orchestration, and strong focus on retrieval accuracy and explainability.

Materials Provided

• /docs/ – Pre‑processed Markdown legal documents with metadata
• /sample_questions.json – Example question format
• /sample_answers_rag.json – Example answer format

Download materials (Benchmark uses unseen questions.)

Deliverable

Implement two functions in Python 3.12 (Poetry project):

def ingest(document_paths: List[str]) -> None

"""Ingest Markdown docs and build the knowledge graph."""

def query(questions: List[str]) -> List[str]

"""Return answers with Vancouver‑style citations grounded in retrieved sources."""

Requirements

• No UI, no API keys provided. Any stack may be used.
• query(...) must support parallel execution (~400 questions in ≤60 min) and show a progress indicator.
• Test thoroughly for correctness and performance before the demo.

Live Demo

• In a 60‑minute live session you will: Receive ~400 unseen questions.
• Run query(...) to produce /answers.json.
• Explain your architecture: how the graph is built, traversed, and used to generate grounded answers.
• Only the developer(s) who wrote the code may present.

Evaluation

Passing requires an overall score above 95%, measured by (LLM as a judge): Faithfulness (grounded, no hallucinations), Relevance (retrieval matches intent), Completeness (covers key legal points), and Clarity (structured, legally coherent writing).