We are looking
for an AI/Computer Vision Engineer to build and optimize real -time video
analytics solutions for SafeSwim.AI. The ideal candidate should have experience.
Developing, training, and deploying deep learning models for object detection,
tracking, and video understanding. You will work closely with product, cloud,
and engineering teams to deliver scalable AI solutions for safety -critical
environments.
Key Responsibilities
· Develop, train, and optimize computer vision
models for real -time object detection and tracking.
· Work with YOLO, RT -DETR, or similar object
detection frameworks.
· Prepare, clean, and annotate datasets for model
training.
· Fine -tune pre -trained models and improve
detection accuracy.
· Evaluate model performance using precision,
recall, mAP, and latency metrics.
· Optimize inference for edge devices and
GPU -based deployments.
· Integrate AI models into production
applications.
· Work with video streams (RTSP, CCTV, IP
Cameras).
· Collaborate with software engineers for
deployment and API integration.
· Troubleshoot model performance and continuously
improve detection accuracy.
· Maintain documentation and experiment tracking.
Required Skills
Computer Vision
· Object Detection
· Image Classification
· Object Tracking
· Instance Segmentation (preferred)
· Video Analytics
AI
& Deep Learning
· PyTorch
· TensorFlow/Keras
· OpenCV
· Ultralytics YOLO
· CNN Fundamentals
Programming
· Python
· NumPy
· Pandas
· Object -Oriented Programming
Data
· Data Annotation
· Dataset Preparation
· Data Augmentation
Deployment
· Docker
· REST APIs
· GPU Optimization
· Linux
Requirements
Preferred Experience
· Experience with live video processing.
· Experience deploying AI models on NVIDIA GPUs.
· Familiarity with DeepStream or TensorRT.
· Knowledge of MLOps fundamentals.
· Experience using Git and Agile methodologies.
Qualifications
· Bachelor's degree in Computer Science, AI,
Electronics, or a related field.
· 2–4 years of hands -on experience in AI/ML or
Computer Vision.