Open to opportunities

Umar Imam

@umarimam

Message

AI Engineer Intern building production-grade RAG and agentic LLM applications.

India

Message

What I'm looking for

I’m looking to build scalable Generative AI systems—RAG, agentic workflows, and streaming chatbots—while collaborating with product teams to ship measurable improvements in latency, accuracy, and real user experience.

I’m an AI Engineer Intern specializing in Generative AI, Agentic AI systems, and LLM-powered application development. I build production-grade RAG pipelines, multi-model LLM orchestration systems, and real-time streaming chatbots that users can rely on.

At Codestore Technologies, I architected and deployed an internal AI chatbot leveraging multi-model LLM orchestration, cutting average employee query resolution time by 40%. I designed a context-aware conversational pipeline with persistent session memory that keeps multi-turn dialogue coherent across 10+ interaction rounds without context degradation.

I also engineer modular prompt templates and retrieval systems to improve accuracy and reduce hallucinations, including FAISS-based semantic document lookup across 500+ internal articles. I’m passionate about deploying scalable AI systems using Streamlit and FastAPI, backed by model evaluation benchmarks for latency, coherence, and task accuracy.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer Intern

Current

Codestore Technologies

Mar 2026 - Present (3 months)

Architected and deployed a production-grade internal AI chatbot using multi-model LLM orchestration, reducing average employee query resolution time by 40%. Built a context-aware RAG and conversational memory pipeline, improving response accuracy by 35% while enabling semantic retrieval across 500+ knowledge base articles.

Orchestration Faiss Prompt Engineering Vector Search Ollama fastAPI