Chaturved
AI/ML Engineer | Computer Vision | Deep Learning | Generative AI | AI Agents
Hire this person
Send a job offer directly to this candidate
About
AI/ML Engineer with hands-on experience developing deep learning, computer vision, generative AI, and AI-agent systems. Experienced in building real-time vision pipelines using Python, PyTorch, OpenCV, YOLO, CNN-based feature extraction, image processing, object detection, and classification. Developed multimodal and agentic AI applications involving real-time audio/visual processing, LLM integration, prompt engineering, and intelligent task orchestration.
Strong experience across model development, feature engineering, evaluation, experimentation, and deployment-oriented application development. Seeking to contribute to AI-powered visual inspection, defect detection, image analytics, and applied computer vision systems.
Experience
AI/ML Engineering Intern at ParkNSecure Pvt Ltd (2025-06 – 2025-07)
- Developed an AI-powered parking intelligence system combining computer vision, NLP, and backend APIs for automated vehicle and parking-slot understanding.
- Implemented real-time vehicle detection and slot-tracking pipelines using computer vision techniques for automated parking-space monitoring.
- Developed Flask-based AI service endpoints integrating Gemini API for natural-language intent recognition and intelligent query handling.
- Designed optimized API workflows with response caching and asynchronous processing, reducing average query latency by approximately 40%.
- Integrated AI inference and application logic into a production-oriented workflow supporting real-time parking information and automated user interaction.
AI/ML Engineering Intern at CodTech IT Solutions (2024-07 – 2024-09)
- Developed end-to-end machine learning pipelines for predictive analytics using Python and scikit-learn.
- Applied feature engineering, SMOTE-based class balancing, cross-validation, and hyperparameter optimization for imbalanced classification problems.
- Performed comparative evaluation across multiple ML algorithms using ROC-AUC, precision, recall, and precision-recall analysis.
- Improved model ROC-AUC from 0.74 to 0.89 through systematic model selection and hyperparameter tuning.
- Conducted 5-fold cross-validation and model evaluation to identify robust candidate models for deployment.
Education
B.Tech in Computer Science & Engineering (AI & ML) – GITAM University, Bangalore (2022-08 – 2026-05)
