Senior Python Full-Stack AI Engineer (PwC – AI Platform, RAG) at Staffinit | Torre

Senior Python Full-Stack AI Engineer (PwC – AI Platform, RAG)

Emma highlights
This highlight was written by Emma’s AI. Ask Emma to edit it.
Full-time

Legal agreement: Contractor

Currency exchange and payroll taxes to be paid by:

Depends on the location of the candidate

Compensation
EUR20 - 40/hour
~USD23.3 - 46.7/hour
Non-negotiable
location_on
Hybrid (City Green Court, Hvězdova, Prague 4-Nusle, Czechia)
Posted about 1 month ago

Responsibilities


Project: - Build an AI platform (RAG, search, document drafting) to automate and scale complex corporate consolidation assessments for PwC. - Duration: 1 year (Start: ASAP). - HackerRank: Yes. - Location: Fully remote (occasional quarterly team sessions in Prague; Prague-based candidates preferred). - Hours: Core US overlap required (minimum 2–6 PM CET, preferred 2–7 PM CET). - Contract: B2B only (must have a valid EU VAT number verifiable in VIES). Python Backend and Platform Engineering: - Core: Python 3.12+, OOP, clean architecture, FastAPI, CLI scripting (argparse, Bash). - Async and Data: Celery, event-driven workflows (RabbitMQ, Azure Service Bus), PostgreSQL, MongoDB. - Data and Reporting: pandas, NumPy, openpyxl (JSON to Excel report generation), batch processing. RAG and LLM Engineering: - Pipeline: End-to-end RAG (ingestion, chunking, embeddings, retrieval, generation). - LLMs and Prompts: OpenAI API (reasoning models, structured output parsing), prompt engineering and versioning (manifest.yaml). - Search and Retrieval: Hybrid retrieval (Vector + BM25), metadata filtering, Qdrant, Azure AI Search (ACS), pgVector. Document Processing and Ingestion: - Extraction and OCR: PyMuPDF (fitz), Tesseract (pytesseract). - Strategy: Clause-aware and section-aware chunking for legal and financial documents. Fullstack Integration and UI Demos: - Internal Tools: Multi-page Streamlit apps, session state, streamlit-aggrid for SME workflows and PoCs. - Fullstack Support: Basic-to-intermediate Node.js and React to maintain and connect frontend integration modules to Python APIs. DevOps and Quality Assurance: - Hygiene: Docker, Docker Compose, Git (small, regular commits), YAML-driven configurations. - Testing: Unit and integration tests for Python services and pipelines. Soft Skills and Nice-to-Haves: - Soft Skills: Autonomous pipeline debugging, strong communication to iterate on prompts and outputs alongside non-technical accounting and audit SMEs. - Nice-to-Have: RAG evaluation frameworks, MCP/FastMCP, LangChain, LangGraph, multi-agent frameworks (CrewAI, AutoGen, TaskWeave), Azure CI/CD. Location Requirement: Please apply only if you are based in one of the accepted countries listed and are able to attend the occasional quarterly team sessions in Prague. Listed countries: Austria, Belgium, Bulgaria, Croatia, Cyprus, Czechia, Denmark, Estonia, Finland, France, Germany, Greece, Hungary, Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta, Netherlands, Portugal, Romania, Slovakia, Slovenia, Spain, Sweden, Northern Ireland