About the Role

We are looking for a passionate and motivated AI Engineer Intern to join our team and work on cutting-edge applications powered by Large Language Models (LLMs). This internship offers hands-on exposure to real-world AI systems, RAG pipelines, vector databases, and modern AI frameworks.

You will collaborate closely with engineering and product teams to build and optimize intelligent AI-powered applications.

What You Will Do

- Assist in designing and developing applications using Large Language Models (LLMs)
- Support the development and optimization of RAG (Retrieval-Augmented Generation) pipelines
- Work with frameworks like LangChain, LangGraph, or similar LLM orchestration tools
- Help integrate and manage vector databases such as Pinecone, Qdrant, Weaviate, or FAISS
- Experiment with prompt engineering techniques to improve AI responses
- Assist in building scalable AI workflows and backend integrations
- Monitor and debug LLM applications using observability tools like Langfuse or similar platforms
- Collaborate with backend and product teams to integrate AI features into applications
- Stay updated with the latest trends and advancements in Generative AI and LLMs

Skills Required
- Basic understanding of LLMs, Generative AI, and AI application workflows
- Familiarity with LangChain, LangGraph, or similar frameworks is a plus
- Understanding of RAG concepts,



embeddings, chunking, and retrieval strategies
- Exposure to vector databases such as Pinecone, Qdrant, Weaviate, or FAISS
- Proficiency in Python preferred (Node.js knowledge is a plus)
- Familiarity with APIs like OpenAI, Anthropic, Gemini, or similar
- Valuable problem-solving and debugging skills
- Strong willingness to learn and experiment with emerging AI technologies

Eligibility
- Final-year students, recent graduates, or candidates pursuing degrees in Computer Science, AI/ML, Data Science, or related fields
- Internship/project experience in AI/ML or backend development is preferred
- Candidates with personal AI projects, hackathons, or open-source contributions are encouraged to apply

Bonus Skills
- Experience building AI chatbots or AI assistants
- Knowledge of FastAPI, Flask, or backend integration
- Exposure to cloud platforms or deployment workflows
- Experience with Git/GitHub and collaborative development

Internship Details
- Duration: 2 Months
- Location: [Remote/Hybrid]

Required Skills

AI MERN

Disclaimer: This job posting qnd Location has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 AI Engineer Intern (LLM / Generative AI) (New Delhi)
🏢 iDreamCareer
📍 New Delhi