Building intelligent systems that transform complex data into actionable insights. Specializing in |
Passionate about unlocking value through machine learning and building production-grade AI systems
Hello! I'm a dedicated Machine Learning Engineer with over 8 years of experience in transforming theoretical concepts into production-ready AI solutions.
My journey began with a fascination for how machines can learn from data, and it has evolved into building scalable machine learning systems that drive real business impact. I specialize in designing end-to-end ML pipelines, from data ingestion to model deployment and monitoring.
Designing neural architectures for computer vision, NLP, and generative AI applications.
Building robust data pipelines and preprocessing workflows for efficient model training.
Containerizing models with Docker, deploying to cloud, and monitoring production performance.
Staying at the cutting edge with latest papers, techniques, and emerging AI paradigms.
Showcasing production-grade ML systems and research implementations
Deep learning pipeline for automated diagnosis using transfer learning with ResNet and EfficientNet architectures. Achieved 96.3% accuracy on chest X-ray classification.
Transformer-based sentiment analysis using fine-tuned BERT and RoBERTa models processing 10K+ reviews per minute across multiple channels.
Ensemble model combining Temporal Fusion Transformers with XGBoost for multi-horizon financial forecasting with uncertainty quantification.
Complete ML lifecycle management with automated training, evaluation, A/B testing, and canary deployments on Kubernetes.
YOLOv8-based detection system for industrial quality control achieving 95% precision with edge deployment on NVIDIA Jetson.
Retrieval-Augmented Generation system with vector search, document chunking, and LLM orchestration reducing support load by 60%.
Multi-variate time series forecasting using N-BEATS and Prophet for smart grid optimization, reducing operational costs by 18%.
Comprehensive model performance monitoring with data drift detection, alerting, and automated retraining triggers using Evidently AI.
Sharing insights, tutorials, and deep-dives on Machine Learning and AI
Deep dive into attention mechanisms, positional encoding, and how transformers revolutionized sequence modeling across every domain.
Learn practical feature engineering techniques including target encoding, feature crosses, and automated feature selection strategies.
A hands-on guide to deploying scalable ML pipelines with experiment tracking, model registry, and automated retraining.
Understanding the math behind diffusion models and implementing a denoising diffusion probabilistic model from scratch.
Exploring message passing, graph attention networks, and real-world applications in social networks and molecular design.
Practical strategies for monitoring data distribution shifts and implementing automated model retraining in production systems.
Interested in collaborating on ML projects or need consulting? Let's talk.