AI Developer Intern

The intern will engage in various tasks, such as developing AI-powered applications with Python and implementing systems based on large language models (LLMs) using frameworks like LangChain. Responsibilities include designing Retrieval-Augmented Generation (RAG) pipelines, working with APIs from OpenAI and Gemini, and managing vector databases with tools like FAISS and Pinecone. Additionally, the intern will automate workflows using AI agents, integrate these systems with web and mobile applications, and debug AI pipelines while collaborating with product, design, and engineering teams to contribute to client projects and internal products.

To qualify, candidates must have a strong command of Python and a solid understanding of large language model concepts and prompt engineering. Experience with frameworks like LangChain and RAG architectures is necessary, along with familiarity with APIs such as OpenAI and Gemini. Knowledge of vector databases, embeddings, and data pipelines is also required, as is basic understanding of Git and version control. Applicants should be comfortable working independently in a remote environment.

• It helps to demonstrate your Python skills through personal projects or contributions to open-source.
• Familiarize yourself with LLM frameworks and provide examples of your experience with LangChain or similar technologies.
• Showcase your understanding of AI concepts like RAG pipelines and data embeddings in your resume or cover letter.
• Having a solid grasp of version control using Git can enhance your candidacy.
• Consider creating a portfolio of any relevant projects that highlight your skills and experiences in AI development.