Python AI Engineer (Local to Chicago Only)

We are only considering candidates based in Chicago. First interview will be on site in the Chicago office with a technical assessment. Please do not apply if this first phase is not possible.

We are looking for an AI Engineer to design, develop, and deploy an intelligent, multilingual chatbot that helps users track their parcels seamlessly. The chatbot will integrate with Snowflake for data retrieval, leverage APIs or web scraping to fetch tracking updates from external systems and run as a containerized solution on Azure. We are seeking to hire an engineer who is passionate about building scalable, AI-powered applications. You’ll work at the intersection of backend development and AI integration, leveraging modern tools like LLMs, MongoDB, Docker, and best coding practices. You’ll be responsible for writing clean, efficient, and maintainable code while working closely product teams to deploy intelligent systems. We need a proactive, self-motivated leader who thrives in a dynamic environment.

Key Responsibilities

• Design, develop, and maintain an AI-powered chatbot capable of handling multi-lingual conversations.
• Implement Retrieval-Augmented Generation (RAG) workflows to improve response accuracy and reduce unnecessary LLM calls
• Integrate AI and LLM tools (e.g., OpenAI, LangChain, Hugging Face) into real-world applications
• Integrate chatbot with Snowflake to fetch tracking data using tracking IDs.
• Develop web scraping and API connectors to external parcel tracking systems
• Deploy and manage chatbot services on Azure using Docker containers.
• Implement vector databases (e.g., Pinecone, FAISS, Chroma) for efficient context management and response caching.
• Ensure code quality through best practices: clean code, testing, and code reviews.

Must-Have Skills

• Programming: Strong proficiency in Python and relevant libraries (e.g., LangChain, FastAPI, BeautifulSoup, Requests
• AI Tools & Frameworks: Experience with OpenAI, Hugging Face, or similar AI APIs
• RAG Implementation: Hands-on experience integrating LLMs with vector databases and retrieval pipelines
• NLP: Strong understanding of prompt design, token usage, embeddings, and language model
• Data Integration: Experience connecting with Snowflake or similar dataware houses.
• Deployment: Knowledge of Docker and Azure container deployments.
• Web Scraping & APIs: Experience building scrapers or integrating with third-party APIs
• Version Control: Familiarity with Git and CI/CD pipelines
• Strong communication skills — able to explain complex AI concepts in simple terms
• Collaborative attitude and openness to feedback

Nice-to-Have Skills

• Familiarity with LLM orchestration frameworks (LangChain, LlamaIndex)
• Exposure to multi-lingual NLP models or translation APIs