| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Original HTTPS Page] |
Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.
You must be logged in to block users.
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseHi, I’m Ritunjay. I’m a software engineer building enterprise AI applications for financial services.
I currently work at Intellect Design Arena, where I build full-stack AI systems on the Purple Fabric platform, ranging from LLM pipelines and multi-agent workflows to databases and backend services. Recent work includes compliance automation, wealth management tools, and lending workflows.
My background spans backend systems, ML infrastructure, and full-stack development. I’ve built web applications with Vue.js and Node.js, engineered large-scale geospatial data pipelines, developed blockchain security analysis systems, and published IEEE research on disease classification. Recently built VectorScale (production vector search at 100M scale with 95% cost reduction) and CodeLens (two-stage ML ranking with 9× model compression).I’ve also worked on forest classification, automated discovery systems, gaming analytics, and satellite network performance analysis.
What drives me is building reliable software that solves real problems, whether that means optimizing backend performance, designing scalable APIs, automating business workflows, or applying machine learning in production systems. I enjoy working across the stack and learning through hands-on projects.
Open to software engineering roles across backend, full-stack, AI engineering, data engineering, and ML. Always learning and happy to contribute to impactful projects.
Production vector search at 100M scale with 95% cost savings. C#/.NET 8 + Python ML, Azure Container Apps, 99.99% uptime.
Python
AI-powered code review — two-stage ML ranking (CodeBERT + distilRoBERTa) on GCP Cloud Run + Vertex AI, dual-stack frontend (Solid.js + Next.js)
HTML
Empirical analysis of LEO satellite network handover behavior using real Starlink performance data. Automated collection of 500+ data points revealing 73% connection stability and optimal elevation…
Jupyter Notebook 4
AI-powered respiratory disease detection using deep learning on audio spectrograms | Published IEEE Research | Multi-class classification of 8 respiratory conditions including COPD, Asthma, and Pne…
Jupyter Notebook 1
| Back | FazBrowse Home | New Git URL |