AI Python Engineer (local to Chicago)

We are seeking a local, Chicago based AI Engineer to design, build, and deploy an intelligent, multilingual chatbot that enables users to seamlessly track parcel shipments. This role combines backend development, AI integration, and cloud deployment to create scalable, production-ready AI applications.

The AI Engineer will work at the intersection of LLM-powered applications, data integration, and cloud infrastructure, developing solutions that integrate enterprise data sources and external systems. The chatbot will connect with Snowflake for tracking data retrieval, leverage APIs or web scraping to obtain updates from external parcel systems, and run as a containerized service within Azure.

The ideal candidate is passionate about building scalable AI-powered systems, writing clean and maintainable code, and collaborating closely with product and engineering teams to deliver intelligent solutions in a fast-paced environment.

This is a full-time, permanent position based in downtown Chicago.

• Design and develop a multilingual AI chatbot capable of handling user inquiries related to parcel tracking
• Implement Retrieval-Augmented Generation (RAG) workflows to enhance response accuracy and reduce unnecessary LLM calls
• Integrate LLM platforms and AI tooling into production-ready applications
• Connect the chatbot to Snowflake to retrieve parcel tracking information using tracking identifiers
• Build and maintain integrations with external parcel tracking systems through APIs or web scraping
• Implement vector databases to manage contextual retrieval and response optimization
• Deploy and manage containerized services using Docker within an Azure cloud environment
• Optimize performance, scalability, and reliability of AI-driven services
• Write clean, efficient, and maintainable code following modern software development standards
• Implement testing, version control, and CI/CD best practices
• Participate in code reviews and continuous improvement initiatives

Qualifications

• Strong proficiency in Python and relevant frameworks and libraries
• Experience building AI-enabled applications using tools such as OpenAI APIs, Hugging Face, or similar LLM platforms
• Hands-on experience implementing Retrieval-Augmented Generation (RAG) architectures
• Knowledge of prompt engineering, embeddings, token optimization, and LLM workflows
• Experience integrating with Snowflake or other modern data warehouses
• Experience deploying containerized applications using Docker in Azure or similar cloud platforms
• Experience integrating with third-party APIs and/or developing web scrapers
• Familiarity with vector databases such as Pinecone, FAISS, or Chroma
• Experience with Git, version control, and CI/CD pipelines
• Strong problem-solving abilities and attention to code quality
• Excellent communication and collaboration skills