Software Engineering Intern, Applied AI

About the Role

Envita Solutions is seeking a Software Engineering Intern to join their Digital Innovation team for the summer. This role focuses on strengthening the foundations of AI-powered applications, including data quality, logging, observability, integrations, and test coverage, while gaining exposure to production-level LLM and agent-based systems. Ideal for students interested in making systems more reliable, readable, and maintainable, and understanding AI application internals.

Key Responsibilities

• Data Quality & Cleanup: Profile, clean, deduplicate, and normalize structured and unstructured datasets; write repeatable scripts and validation checks.
• Logging & Observability: Improve logging, error handling, and monitoring across Python and C# services and data pipelines.
• Integration Development: Build and harden integrations using REST APIs, webhooks, and scripting.
• Code Quality & Technical Debt: Refactor existing code, add automated tests, improve documentation, and address backlog items.
• AI Application Support: Contribute to LLM-based features such as structured data extraction, retrieval (RAG / vector search), and agent workflows, including building evaluation and test harnesses.
• Prototyping: Deliver small, well-scoped proof-of-concept tools or automations.
• Cross-Team Collaboration: Partner with technology and business teams to understand data and system usage and identify areas for improvement.
• Engineering Practices: Work within the team's standard development workflow, including version control (Git/GitHub), code review, issue tracking, and CI. Communicate progress clearly.

Requirements & Tech Stack

• Required: High School or Equivalent.
• Preferred: Bachelor's Degree or in progress (sophomore, junior, senior, recent grad, or 1st/2nd Master's student) in Computer Science, Software Engineering, AI/ML, Statistics/Mathematics, or a related field.
• Academic, internship, or project-based experience writing Python for real applications beyond coursework.
• Experience consuming or building REST APIs and/or webhook-based integrations.
• Familiarity with Git-based workflows (branching, pull requests, code review).
• Exposure to LLM tooling preferred: prompt engineering, LLM APIs, agent frameworks (e.g., LangGraph, Claude Code, or similar), or RAG / vector search / embeddings.
• Coursework or project experience in machine learning, databases, or data engineering is a plus.
• Proficiency in Python, including writing clean, testable, well-structured code.
• Working knowledge of SQL and comfort working with messy, real-world data.
• Understanding of software engineering fundamentals: testing, debugging, logging, error handling, and version control.
• Foundational understanding of how LLM-based applications are built and interest in going deeper.
• Familiarity with cloud platforms (Azure preferred) and containerized deployments is a plus.
• Strong problem-solving skills and persistence.
• Effective communication skills, able to document work and explain technical decisions.
• Must be able to make in-office commute.