Results-driven Machine Learning & MLOps Engineer with 3+ years of experience in designing, developing, and deploying scalable AI systems across computer vision and large language models. Passionate about developing scala…
Results-driven Machine Learning & MLOps Engineer with 3+ years of experience in designing, developing, and deploying scalable AI systems across computer vision and large language models. Passionate about developing scalable, real-world AI systems and Generative AI solutions that drive measurable business impact.
Developed and deployed computer vision models (YOLOv4, YOLOv8, Transformers) for object detection, segmentation, and tracking applications.
Built and deployed REST APIs using FastAPI and Flask for serving ML models in production.
Implemented edge device deployment of optimized ML models for real-time inference in low-latency environments.
Performed model optimization, evaluation, and monitoring in production environments.
Engineered video analytics and geospatial AI solutions integrated with Google Maps API, Cloud Vision API, Firebase, and Geolocation APIs.
Utilized AWS (S3, EC2) for scalable storage, compute, and deployment.
Worked closely with clients (India & international) to deliver PoCs and production-ready AI systems.
Developed and deployed computer vision models (YOLOv4, YOLOv8, Transformers) for object detection, segmentation, and tracking applications., Built and deployed REST APIs using FastAPI and Flask for serving ML models in production., Implemented edge device deployment of optimized ML models for real-time inference in low-latency environments., Performed model optimization, evaluation, and monitoring in production environments., Engineered video analytics and geospatial AI solutions integrated with Google Maps API, Cloud Vision API, Firebase, and Geolocation APIs., Utilized AWS (S3, EC2) for scalable storage, compute, and deployment., Worked closely with clients (India & international) to deliver PoCs and production-ready AI systems.
Lane detection was developed using a customized YOLOv11 model optimized for real-time object localization and segmentation of road lanes. The dataset was annotated with diverse road conditions to improve robustness under varying lighting and weather scenarios. After training and validation, the model was converted to TensorRT and optimized for low-latency inference. Finally, the solution was deployed on an edge device NVIDIA Jetson Nano for real-time, on-device lane detection.
نظام التوظيف التشغيلي المعتمد على الذكاء الاصطناعي أولاً، الذي يوحّد ويؤتمت دورة التوظيف بالكامل للمؤسسات الحديثة حول العالم.
د.جوب منطقة حرة ذ.م.م. 2026 © جميع الحقوق محفوظة
