Aldiyar Dinislam

Middle Computer Vision / ML Engineer. I build real-time video and audio analytics systems: object detection and tracking, face detection and recognition, appearance attributes, pose-based aggression detection, and ASR with Whisper (ru, en, kk). MLOps: ONNX, TensorRT, Docker, FastAPI, DVC, MLflow.

Networking with computer vision and MLOps engineers, sharing experience on production inference, finding new roles and interesting projects, and getting feedback on my solutions and current tasks.

I share practical experience in computer vision, real-time inference, model optimization with ONNX and TensorRT, and deployment via Docker and FastAPI. Happy to help with detection, tracking, face recognition, and ASR.