Vinoothna Nadikatla

I’m a M.Tech candidate in Applied AI, focused on the full lifecycle of Machine Learning model development and deployment. I build Explainable Deep Learning and Gradient Boosting solutions, using SHAP and Computer Vision to deliver actionable insights in domains like Predictive Maintenance and Cybersecurity.

In my projects, I developed an “Explainable Hybrid Gradient Boosting–Deep Learning Framework for Bearing Fault Classification” with 98.34% accuracy and real-time industrial fault diagnosis, and built an agentic multimodal AI assistant with real-time speech, vision, and LLM reasoning using Groq and Lang Graph. I’ve also automated cybersecurity incident triage—reducing response time by 30%—and created production-style apps and pipelines like a used car price prediction Streamlit app (90% accuracy) and a YouTube data harvesting/warehousing workflow that enabled 20% faster reporting. I’m now seeking a challenging AI Engineer or Data Scientist role where I can drive automation, reliability, and explainability from idea to deployment.