Generative AI Engineer Intern

Role Overview

As an AI Engineer Intern, you’ll work on building agent-grade intelligence systems, with a strong focus on long-term memory architectures, knowledge graphs, and Graph + LLM hybrid reasoning. You will also work on core AI engineering tasks such as LLM orchestration, embeddings, retrieval, and agent workflows.

Responsibilities

• Design and prototype knowledge graph-based memory systems.
• Implement entity extraction, relationship mapping, and memory linking.
• Build Graph + LLM pipelines for contextual recall and reasoning.
• Explore hybrid architectures combining vector search and graph traversal.
• Work with LLMs for reasoning, summarization, extraction, and planning.
• Implement embedding pipelines and retrieval mechanisms.
• Assist in building agent workflows including planning, memory recall, and execution.
• Optimize prompts, tools, and context windows.

Requirements

• Strong understanding of LLMs and prompt-driven systems.
• Solid programming skills in Python or Node.js.
• Familiarity with embeddings and semantic search.
• Conceptual understanding of knowledge graphs (nodes, edges, relations).
• Ability to think in systems, data flow, and abstractions.
• Comfort working with APIs and async workflows.

Nice to Have

• Experience with graph databases like Neo4j, ArangoDB, or Amazon Neptune.
• Exposure to GraphRAG, memory graphs, or agent memory frameworks.
• Familiarity with LangChain, LlamaIndex, or CrewAI.
• Understanding of vector databases such as Pinecone, Weaviate, or FAISS.

Skills

• Python
• LLMs
• LangChain
• Vector Databases
• Knowledge Graphs