RAG (Retrieval-Augmented Generation) Intern
Join our engineering team for a 3 Months / 6 Months internship and gain real-world experience working on production applications.
3 Months / 6 Months
Remote / On-site (Noida)
Stipend Available
Role Overview
This internship is designed to help you move beyond classroom learning. If you're a student or early-career developer who has learned Python but hasn't yet had the opportunity to work on a real project, this internship is designed to help you bridge that gap.
Core Responsibilities
- Implement document ingestion and chunking logic
- Extract text and generate embeddings
- Build vector search and semantic retrieval systems
- Generate context-aware LLM responses
What You Will Learn
- Advanced RAG architectures
- Vector database indexing (Qdrant, Pgvector)
- Optimizing LLM context windows
- Building citation and hallucination-prevention systems
Ready to apply?
Send us your resume and any relevant portfolio/GitHub links. We review applications on a rolling basis.
Email Your ApplicationRequired Skills
PythonLLMsVector DatabasesGit
Good to have
LangChainLlamaIndexFastAPI
Eligibility
Students / Freshers. Students pursuing B.Tech, BCA, MCA, or career switchers with relevant technical skills. Demonstrated ability to write basic code is required.
Explore Other Roles
Not the right fit? View our other open positions or check back later.