About the Role
We are looking for a Principal Engineer – AI Systems and Automation with deep expertise in Python and JavaScript to join our Data Team. You will play a key role in building scalable systems that process restaurant menu data at scale using Large Language Models (LLMs) and AI Agents. This is a high-impact role at the intersection of AI and data engineering. You’ll help us improve the speed, accuracy, and intelligence of our menu ingestion pipelines through automation, model integration, and smart task orchestration.

Key Responsibilities

• Take ownership of existing software tools and systems—evaluate, run, debug, and extend them to accelerate menu data processing workflows.
• Contribute to our restaurant menu processing pipeline, including matching menu items to cocktails and other alcohol beverage products in our proprietary database.
• Design and implement scalable back-end services in Python for data extraction, transformation, and classification of restaurant menus.
• Collaborate with data scientists and ML engineers to integrate and productionize LLM-based pipelines.
• Develop and manage agent-based orchestration workflows (e.g., LangGraph or similar tools) to enable intelligent, modular task processing.
• Optimize data pipelines for performance, robustness, and cost-efficiency.
• Write clean, well-tested, and maintainable code; participate in code reviews and mentor junior developers.

Requirements

• 7+ years of professional software development experience.
• Advanced proficiency in Python and JavaScript.
• Strong working knowledge of PostgreSQL (including writing complex queries, indexing, and performance tuning).
• Practical experience using Snowflake for data warehousing, querying, and analytics.
• Hands-on experience with CI/CD tools like Jenkins, GitHub Actions, or similar.
• Experience building and scaling data-intensive applications.
• Hands-on experience with LLM frameworks (LangChain, LangGraph, OpenAI API, etc.).
• Experience working with cloud platforms like AWS or GCP in a production environment.
• Familiarity with agent-based orchestration or workflow tools.
• Experience working with structured and unstructured data (JSON, HTML, PDFs, etc.).
• Excellent debugging and problem-solving skills.
• Proficiency with Jira for sprint planning, issue tracking, and agile team collaboration.
•  

Nice to Have

• Experience with vector databases, embeddings, and semantic search.
• Familiarity with web scraping frameworks like Playwright and Scrapy.
• Knowledge of Snowflake.
• Experience with cloud platforms (AWS, GCP, or Azure).