AI Infrastructure & RAG Engineering Intern

About the Role

We are looking for an AI Infrastructure & RAG Engineering Intern to work closely with our engineering team on backend infrastructure, data systems, retrieval-augmented generation (RAG), semantic search, and AI-powered applications. This is a hands-on engineering role involving real product infrastructure, databases, APIs, cloud systems, and LLM pipelines.

What You’ll Work On

• Design, develop, and maintain PostgreSQL databases
• Build database synchronization and data ingestion pipelines
• Develop REST APIs and backend services
• Work with Node.js / TypeScript / Deno
• Build and optimize RAG pipelines
• Implement embeddings, vector search, and semantic retrieval
• Work with pgvector and PostgreSQL-based vector infrastructure
• Develop prompt engineering and LLM workflows
• Build real-time data aggregation and processing systems
• Integrate and manage AWS cloud infrastructure
• Improve retrieval quality, latency, reliability, and scalability of AI systems
• Debug, test, document, and optimize production-oriented systems

Requirements & Tech Stack

• Strong understanding of PostgreSQL and relational databases
• Familiarity with backend development and REST APIs
• Working knowledge of Node.js, TypeScript, or Python
• Understanding of Git and GitHub
• Basic understanding of AI/LLM applications
• Understanding of RAG, embeddings, or semantic search
• Strong problem-solving and debugging ability

Good to Have

• Experience with pgvector
• Experience building RAG applications
• AWS experience
• Deno experience
• Experience with vector databases
• Experience with real-time systems / WebSockets
• Experience with LLM APIs
• Knowledge of data pipelines and asynchronous processing
• Understanding of database indexing and query optimization

Who Should Apply

We are looking for someone who enjoys building systems, not just following tutorials. Strong backend fundamentals combined with genuine hands-on experience in AI/LLM projects are highly valued. Candidates with personal projects, GitHub repositories, deployed applications, or previous experience building RAG/AI systems are encouraged to apply.

Stipend

Up to ₹5,000 per month — performance-based. Performance will be evaluated based on technical contribution, quality of implementation, ownership, consistency, problem-solving, and ability to deliver assigned engineering work.