Tech Stack

Description

As an AI Agent Engineering Intern, you will collaborate with engineering and product teams to build, integrate, and deploy intelligent AI agents using modern web frameworks, LLM APIs, and tooling pipelines. You'll gain hands-on experience from prototyping to production, working on real customer use cases.

Requirements

• Proficient in writing clean, maintainable Python code
• Hands-on backend development experience with Django, FastAPI, or Express
• Excellent communication, documentation skills, and experience collaborating in agile teams
• Experience with prompt engineering frameworks (e.g., LangChain) is a plus
• Understanding of cloud platforms (AWS Lambda, Vercel, GCP Cloud Functions) is a plus

Responsibilities

• Agent prototyping and development with prompt engineering for hallucination detection and conversation resolution
• Test and validate AI agent accuracy using internal datasets and tools
• Integrate backend APIs supporting RAG, knowledge bases, and custom toolchains
• Craft, test, and fine-tune prompts for various use cases; set up CI/CD pipelines for prompt versioning and deployment
• Embed agents into web, chat, and API environments; implement monitoring and observability (logs, dashboards)