Python Developer (GenAI, Data Visualization)

Description

Our project leverages cutting-edge technologies to revolutionize the learning experience. By utilizing advanced Large Language Models (LLMs), we generate custom training scenarios tailored to individual needs. These scenarios are seamlessly integrated into a digital twin environment, creating an immersive and highly interactive training platform.

Requirements

We are seeking a Python Developer to join our GenAI initiative, where the goal is to enable AI-driven data visualization. The developer will work closely with the AI team to integrate LLM-powered prompt responses into Apache Superset dashboards, building intuitive and interactive data experiences.

• Strong proficiency in Python (3.8+), with experience in backend development.
• Hands-on experience with data visualization tools such as Plotly, Dash, Matplotlib, or Apache Superset.
• Solid understanding of FastAPI and building production-grade APIs.
• Experience with PostgreSQL and SQLAlchemy for ORM and data management.
• Familiarity with design patterns and clean code principles.
• Proficiency in Git for collaborative development.
• Experience containerizing applications with Docker.
• Exposure to LangChain / LangGraph (or willingness to learn) for LLM integration.
• Strong problem-solving skills and ability to work in a cross-functional team.
• Bonus: Knowledge of cloud deployment (AWS/GCP/Azure) and CI/CD practices.

Job responsibilities

• Develop, maintain, and optimize Python-based services for data visualization and AI integrations.
• Collaborate with the AI/ML team to consume LLM outputs and translate them into dynamic visualizations.
• Implement APIs using FastAPI for interaction between AI components, Superset, and backend services.
• Build and enhance data visualization pipelines leveraging Superset, Plotly (or similar frameworks), and custom charting solutions.
• Design scalable solutions using best practices in design patterns and software architecture.
• Work with PostgreSQL + SQLAlchemy for data querying, modeling, and storage.
• Containerize and deploy applications using Docker.
• Collaborate via Git for version control and CI/CD pipelines.
• Explore and implement LLM orchestration frameworks such as LangChain or LangGraph for advanced prompt workflows.
• Ensure system performance, scalability, and reliability for real-world analytics use cases.