Computer Vision

Experience: 4+ years

Location: Remote

Roles & Responsibilities

● Strong expertise in Computer Vision: Experience with Face Detection, Object Detection,

Object Counting, Tracking, and Pose Estimation on CCTV or similar video data.

● Proficiency with Deep Learning frameworks: Hands-on experience with TensorFlow,

PyTorch, or Keras for developing and training computer vision models.

● Experience with Object Detection models: Familiarity with models like YOLO, SSD, Faster

R-CNN, and knowledge of real-time detection.

● Object Tracking algorithms: Knowledge of multi-object tracking (MOT) algorithms and

experience in tracking moving objects in video footage.

● Pose Estimation: Familiarity with techniques like OpenPose or MediaPipe for detecting

human posture and activities in video streams.

● Image Processing & Enhancement: Solid understanding of image processing techniques

(e.g., filtering, edge detection, transformation, enhancement) using OpenCV or similar

tools.

● Machine Learning & AI Fundamentals: Strong knowledge of classical machine learning

algorithms and how they integrate with deep learning for model improvement.

● Generative AI: Exposure to generative models like GANs, diffusion models, or similar, and

their potential application in Computer Vision.

● Programming Skills: Proficiency in Python, with experience in relevant libraries like

NumPy, Pandas, and Scikit-learn.

● Experience with Cloud Services: Knowledge of cloud platforms like AWS or Azure for

deploying models in a production environment.

● Strong Analytical and Problem-Solving Skills: Ability to troubleshoot complex algorithms

and optimize performance for real-time use cases.

● Familiarity with MLOps: Understanding of CI/CD pipelines, model versioning, and

deployment best practices in an ML context.

● Collaboration & Communication: Ability to work effectively within a team, collaborate

with different departments, and communicate technical results to non-technical

stakeholders.