Asfand Yar

Engineered and deployed two voice-based AI agents, automating complex customer interaction workflows and reducing manual follow-up efforts by 53%.

Developed an autonomous post-session feedback bot, collecting user reviews, sentiment, and session ratings to enhance service insights and improve customer retention.

Built a proactive membership renewal voice agent, guiding users through the renewal process and improving customer engagement rates.

Integrated advanced speech recognition, conversational logic, and CRM systems, ensuring seamless and intelligent customer communication.

Developed a comprehensive FedX-GAN system for anomaly detection on CICIDS2017/2018 datasets, significantly enhancing system robustness through synthetic data generation.

Integrated encoder-LSTM pipelines to capture temporal patterns in network traffic, achieving 97% client-side classification accuracy while maintaining strict data privacy.

Implemented efficient, privacy-preserving training methodologies across distributed nodes, resulting in improved communication efficiency and reduced latency during model training.

Led development of a Vertical Federated Learning (VFL) framework, successfully processing data from 20 heterogeneous clients while preserving data privacy across partitions.

Implemented client-side Variational Autoencoders (VAEs) and Attention-based CNNs to extract rich local features without exposing sensitive raw input data.

Designed and optimized a server-side Transformer-based fusion model and multiclass classifier, detecting over 17 distinct cyberattack types with 98% accuracy.

Conducted comprehensive performance validation using precision, recall, and F1-score metrics, while simultaneously improving communication efficiency over multiple federated rounds.

Designed and implemented an AI-powered facial recognition attendance system, increasing access control security by 40% and reducing manual processing time by 75%.

Created an innovative ML-based sign language detection system using OpenCV and CNNs, improving accessibility for hearing-impaired users and gaining recognition from local disability advocacy groups.

Optimized image processing models for medical image analysis, resulting in a 30% increase in detection speed without compromising accuracy, enabling faster clinical diagnosis.

Led a cross-functional team of AI engineers to deliver proof-of-concept solutions for real-time object detection using YOLO, subsequently adopted for production.

Developed and deployed computer vision models for industrial automation, reducing manual monitoring requirements by 60% and improving detection accuracy by 25%.

Built advanced NLP-based sentiment analysis tools for social media monitoring, increasing accuracy by 15% over baseline models and providing reliable marketing insights.

Successfully deployed multiple ML models via Flask APIs, standardizing interfaces, simplifying web integration, and reducing implementation time by 40%.

Optimized deep learning architectures, reducing model size by 35% and inference time by 28%, enabling efficient deployment on resource-constrained edge devices.

Conducted extensive R&D on AI-based video editing tools, automating content generation workflows and reducing production time by 50%.

Implemented sophisticated AI pipelines for sentiment analysis on social media data, improving insight extraction speed by 40% and enabling real-time trend analysis.

Contributed to the development of EEG-based brain signal analysis systems for healthcare diagnostics, identifying neurological patterns with 85% accuracy using advanced ML models.