Shiva Shrestha
AI Engineer.
I take foundation models past benchmarks into real-world domains where data is messy and failures matter.
Currently shipping visquery.com & web-intelligence · Open to AI roles
Recent writing
- Fine-tuning a VLM is mostly not a training problem. Here are the five decisions that mattered more.Medium · May 2026
- What I Learned Measuring My Own RAG SystemMedium · May 2026
- Fine-tuning CLIP on a Niche Domain: How I Got +26pp Accuracy on Architectural Stylesdev.to · May 12, 2026
- Building a RAG Evaluation Harness That Actually Catches Problemsdev.to · May 5, 2026
Background
Previously at AREP in Paris, where I built CLIP-based multimodal search and image-tagging systems used by internal teams. Before that, three years building ETL pipelines and large-scale web scraping at Procit, and earlier work annotating radar and LiDAR data for autonomous driving perception models at CloudFactory. MSc in Computer Science (Data Science & Analytics) from EPITA Paris, 2025.