AI Software Engineer Intern: Build Enterprise AI & LLM Apps

IBM; New York (NY); On-site; USD 34,000 - 55,000; Full time

Job summary

IBM Software is hiring an AI Software Engineer Intern to transform challenges into AI-powered software. You will work with large language models, integrate APIs and enterprise data, and contribute from prototype through testing.

This internship offers hands-on exploration of agent workflows, tool calling, and reliability improvements. Role requires strong fundamentals, Python proficiency, and hands-on LLM experience.

Qualifications

• Strong software engineering fundamentals, including data structures, algorithms, software design and testing.
• Proficiency in Python and experience building applications that integrate APIs.
• Hands-on experience building an application or prototype with LLMs and explaining its testing.
• Systematic debugging mindset; ability to translate problems into requirements, prompts and criteria.
• Familiarity with Git and clear technical communication; quick learner and team player.

Responsibilities

• Design, build, and test AI-powered features addressing real developer and client needs with guidance.
• Integrate LLMs, APIs, and enterprise data into applications, exploring agent workflows.
• Write specifications and prompts; review and test code; improve AI outputs and reliability.
• Debug across model interactions, application code, APIs, and systems to find root causes.
• Collaborate via Git, code reviews, and technical discussions; document work and iterate on feedback.

Skills

Python

LLM integration

Algorithms

Data structures

Git

APIs

Debugging

Prompt engineering

Communication

Education

High School Diploma/GED

Bachelor's Degree

Tools

Git

APIs

LLMs

Python

Job description

IBM Software is hiring an AI Software Engineer Intern to transform challenges into AI-powered software. You will work with large language models, integrate APIs and enterprise data, and contribute from prototype through testing.

This internship offers hands-on exploration of agent workflows, tool calling, and reliability improvements. Role requires strong fundamentals, Python proficiency, and hands-on LLM experience.