Python Developer Intern – RAG / Agentic AI
About the Role:
We are seeking a highly motivated Python Developer Intern with hands-on interest or
experience in Generative AI, RAG (Retrieval-Augmented Generation), and Agentic AI
systems. In this role, you will work closely with engineering and AI teams to build intelligent
applications, develop AI-powered workflows, and contribute to cutting-edge projects
involving LLMs, vector databases, AI agents, and knowledge retrieval systems.
Key Responsibilities:
- Develop and maintain Python-based applications, APIs, and backend services for AI
solutions.
- Assist in designing and implementing RAG pipelines using embeddings, vector
databases, and LLMs.
- Build and integrate Agentic AI workflows involving tool calling, multi-step
reasoning, task orchestration, and autonomous agents.
- Develop REST APIs using FastAPI or Flask to serve AI models and AI-powered
applications.
- Work with data ingestion, preprocessing, transformation, and retrieval pipelines.
- Support experimentation with foundation models such as GPT, Claude, Llama, or
other LLMs.
- Implement prompt engineering, evaluation frameworks, and AI model testing
processes.
- Collaborate with senior engineers to optimize performance, improve retrieval
quality, and enhance AI system reliability.
- Participate in code reviews, sprint planning, documentation, and Agile development
activities.
Required Skills:
- Strong Python programming skills, including OOP, data structures, and debugging.
- Understanding of REST APIs, JSON, and backend development concepts.
- Familiarity with Git/GitHub and software development best practices.
- Basic understanding of Machine Learning and Generative AI concepts.
- Knowledge of vector embeddings, semantic search, or information retrieval
concepts.
- Strong analytical and problem-solving skills.
- Ability to learn quickly and work in a collaborative environment.
Preferred Skills:
- Experience with RAG frameworks such as LangChain, LangGraph, LlamaIndex, or
Haystack.
- Familiarity with Agentic AI architectures, tool calling, function calling, and
workflow orchestration.
- Experience with vector databases such as Pinecone, Qdrant, FAISS, Weaviate, or
Chroma DB.
- Exposure to LLMs and prompt engineering techniques.
- Experience with FastAPI, Flask, or Django.
- Knowledge of cloud platforms such as AWS, Azure, or GCP.
- Familiarity with Docker and containerized deployments.
Education
- Pursuing a bachelor’s or master’s degree in computer science, Artificial Intelligence,
Machine Learning, Data Science, Engineering, or a related field.