Full stack Engineer (AI & Data Pipelines)

About Patronus:

Patronus is a pioneering provider of data privacy solutions, committed to enabling businesses to build trust and compliance with their customers through privacy-first practices. Our innovative data privacy stack empowers companies to navigate the complexities of data privacy regulations while fostering transparency and accountability. Join us in our mission to redefine data privacy in the digital age

Key Responsibilities:

• ETL & Backend: Architect and build smart, LLM-driven ETL pipelines to deliver ingested and structured data
• Frontend: Build a responsive web platform to present a basic visual output (table or chart)
• AI Integration: Develop and integrate AI-driven features (including chatbot functionality) to interact with the processed data
• Database Management: Set up and manage the database to house the extracted metrics
• Documentation: Write clear documentation describing the data sources used , extraction methods , and any assumptions and limitations

What You Will Build:

• A robust pipeline that demonstrates reliable ingestion from distinct external sources
• A system capable of producing consistent, comparable metrics
• A scalable foundation that can be clearly extended to additional metrics and sources without redesign

Tech Stack & Relevant Libraries:

• Backend & ETL (Python): Python (FastAPI or Flask), Pandas/NumPy (for data normalization), and scraping/ingestion tools (e.g., BeautifulSoup, Playwright, Selenium)
• AI & LLM Orchestration: LangChain, LlamaIndex, and direct integration with LLM APIs (OpenAI, Anthropic, etc.) for smart data extraction from unstructured sources
• Frontend (React / Next.js): React, Next.js, and modern styling libraries (Tailwind CSS, Material-UI)
• Data Visualization: Recharts, Chart.js, or D3.js for rendering responsive charts and data tables
• Database: Relational databases (PostgreSQL/MySQL) or NoSQL options, optionally paired with Vector Databases (ChromaDB, Pinecone) for the AI chatbot context

Requirements:

• Proven experience building backend services and data extraction/ETL pipelines in Python.
• Strong proficiency in React and Next.js for frontend UI development.
• Hands-on experience integrating and prompting LLMs for smart data extraction.
• Self-starter mentality with the proven ability to work completely autonomously and drive a project end-to-end.