AI Software Engineer Intern
Datics AI · Lahore
- Develop Multi-Model Orchestration: Developed high-speed AI apps using LangChain and LangGraph, integrating Groq (Llama 3.3) and Gemini 3.1 for optimized latency and reasoning.
- Advanced RAG & Vector Search: Built persistent RAG pipelines with FAISS and local HuggingFace embeddings, enabling offline semantic search and context-aware responses.
- Full-Stack Streaming: Designed FastAPI and Node.js services with SSE (Server-Sent Events) for real-time token streaming and MongoDB for stateful chat management.
