GenAI / AI Intern
Work on production AI systems — build RAG pipelines, chat agents, integrate LLM APIs with guardrails, and develop Python FastAPI backends. Fine-tuning experience is a plus.
About the role
Join the WebbyButter AI engineering team and ship real GenAI features for enterprise clients. You will pair with senior engineers on retrieval-augmented generation pipelines, conversational agents and LLM integrations that go to production, not prototypes.
What you will do
- Build and evaluate RAG pipelines over client documents and knowledge bases
- Develop chat agents with tool calling, memory and guardrails
- Integrate LLM APIs (OpenAI, Anthropic, Groq, open-source models) into Python FastAPI services
- Write clean, tested Python code and document what you build
- Present your work in weekly demos and iterate on feedback
What we are looking for
- Solid Python fundamentals and comfort with REST APIs
- Hands-on exposure to at least one LLM API or framework (LangChain, LlamaIndex, Vercel AI SDK or similar)
- Understanding of embeddings, vector search and prompt design
- Basic Git workflow and ability to work in a fast-moving team
- Available for a 3-6 month internship, full-time hours preferred
Nice to have
- Fine-tuning or evaluation experience with open-source models
- Familiarity with FastAPI, PostgreSQL or a vector database
- Personal or academic GenAI projects you can show
Key skills
About WebbyButter AI
WebbyButter is an AI-first software company headquartered in Vadodara, Gujarat, India. We build production AI systems for enterprises and funded startups: RAG pipelines, AI agents, intelligent document processing, computer vision and the web products around them. All current roles are based at our Vadodara office.