Intern for AI Engineering and Data Science

Role overview

• check_circle Build & Deploy AI Applications Help develop AI applications (chatbots, RAG knowledge assistants, text to SQL) and contribute to deployment and upgrade processes.
• check_circle Automate Testing & Evaluation Contribute to automated testing frameworks that evaluate model performance, retrieval accuracy (RAG), and agent decision making before production.
• check_circle Develop Retrieval Pipelines Help engineer retrieval systems including chunking strategies, metadata management, embedding generation, and vector database indexing.
• check_circle Monitor & Optimize Assist with monitoring for system performance, latency, errors, and costs. Help build dashboards to track user interactions and model behavior.
• check_circle Curate Knowledge Bases Help build and maintain domain specific knowledge bases (agronomy, grain, logistics) using automated pipelines.
• check_circle Data Engineering Work with internal systems and SQL databases (Snowflake) to feed data into AI models and process outputs.
• check_circle Collaborate & Communicate Work with data engineers and domain experts to identify high impact use cases and present technical findings to stakeholders.

Basic qualifications

• Pursuing a degree in Computer Science, Data Science, Engineering, Statistics, or a related field (or equivalent practical experience).
• Hands on Build Experience You have built at least one AI enabled application (e.g., chatbot, RAG system, agent) and can explain how it works.
• AI Native Workflow You are comfortable using AI coding assistants (Cursor, GitHub Copilot, Claude Code, etc.) to accelerate your development.
• Core Tech Stack Proficiency in Python and SQL. Comfort with REST APIs and Git version control.
• Problem Solving Ability to break down complex problems, debug systems, and learn new technologies quickly.

Preferred qualifications

• Experience with LLM Evaluation Familiarity with frameworks or methods for evaluating the quality of LLM outputs (e.g., RAGAS, TruLens, or custom metrics).
• DevOps, CI, CD Exposure Understanding of continuous integration/deployment concepts, containerization (Docker), or automated testing.
• Cloud & Data Experience with Snowflake, Azure, or similar cloud data platforms.
• Vector Search Understanding of vector databases, embeddings, and semantic search concepts.
• Frontend Skills Ability to build quick prototypes using Streamlit or similar tools.
• Real World Impact Contribute code that real employees use to solve real agricultural problems.
• End to End Exposure See projects through from the “business case” phase to deployment and monitoring, with guidance from senior team members.
• Mentorship Work directly with experienced data scientists and engineers who will help you grow your technical and professional skills.
• Domain Knowledge Learn how AI is applied in the complex world of modern agriculture and supply chain logistics.
• This internship is based in our Omaha office with some hybrid remote work possible.

About the company