Graphrag Developer Challenge

Bullaki; Bolzano; Remoto; EUR 30.000 - 50.000; Part-time

Descrizione del lavoro

A tech-driven company in Italy seeks a Senior RAG Systems Developer for a contract/freelance role. You will build a high-accuracy prototype for legal document reasoning using Python. The role requires expertise in graph-based retrieval systems and will be evaluated through a benchmark test. Successful candidates may be invited for a long-term position with competitive compensation.

Competenze

• Expert in graph-based retrieval systems.
• Experience in building knowledge graphs and traversal.
• Ability to implement parallel execution in code.

Mansioni

• Build a high-accuracy prototype for legal document reasoning.
• Prepare for a 60-minute live demo.
• Explain architecture and design decisions in code.

Strumenti

Python 3.12

Poetry

Descrizione del lavoro

GraphRAG Developer Challenge – Legal Document Processing (Prototype)

• Role: 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: [e-mail]

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).

Payment & Next Steps

If you pass, you'll receive $600 USD after verification of reproducibility and hand‑over of the repo (codebase, Poetry lock, run instructions, brief tech note). Top performers may be invited to interview for a long‑term paid role. Failure to pass or complete within 60 minutes = no payment (you keep your code).

Key Priorities

• Parallelization, graph‑based reasoning, correctness, and explainability.

Note for Agencies

We will not engage in pre‑contract discussions with agencies. If an agency wishes to propose a developer, communication will proceed only after that developer passes the benchmark test. This ensures time efficiency and direct technical validation.