About Me

I'm Ranvir Virk, an AI engineer and data scientist currently pursuing my Master's at UTS. My work sits at the intersection of deep learning, natural language processing, and multi-agent systems.

Previously, I graduated with an MS in Computer Science from Indiana University, and interned at Postman where I architected an agentic AI workflow using CrewAI, LangChain, and ChromaDB — building a multi-agent system for semantic code retrieval that reduced query latency by 40%.

During my time at IU's Luddy School of Informatics as a Research Assistant, I worked on vision transformers, dataset curation, and interpretability research. I've published work in the Journal of Open Humanities Data and contributed to projects spanning computer vision, recommender systems, and data engineering.

I believe the best engineering happens when you deeply understand both the problem domain and the tools at your disposal. I like building systems that are not just technically impressive, but genuinely useful.

When I'm not writing code or training models, you'll find me behind a camera, exploring photography as a creative counterbalance to the analytical work.

Technical Focus

Languages: Python, SQL, R
ML/AI: PyTorch, TensorFlow, LangChain, CrewAI, Hugging Face, Scikit-learn
Data: Spark, DuckDB, Pandas, ETL pipelines, vector databases (ChromaDB, FAISS)
Infra: Docker, AWS, GCP, Vercel, CI/CD, MLflow

Let's Connect

I'm always open to conversations about AI, travel, or anything under the sun. Feel free to reach out via email or connect on LinkedIn.