Description

You will own the development and optimization of computer-vision algorithms for object detection, primarily using YOLO-based models. You are responsible for fine-tuning and retraining off-the-shelf models, applying quantization and distillation to optimize them for edge deployment. You containerize FastAPI-based web services using Docker and publish results to message brokers. You operate within production architecture using Kubernetes and Google Cloud Platform. Proficiency in Python and TypeScript is required to support scalable architectures.

This role is on-site.

Responsibilities

• Fine-tune and retrain YOLO-based models for object detection tasks.
• Apply quantization and distillation techniques to optimize models for edge deployment.
• Containerize FastAPI-based web services using Docker and publish results to message brokers.
• Operate and maintain production infrastructure using Kubernetes and Google Cloud Platform.
• Develop scalable services using Python and TypeScript.

Required Skills

• Strong experience with computer-vision algorithms, specifically YOLO-based models.
• Proficiency in Python and TypeScript for scalable architecture development.
• Docker proficiency for containerizing web services.
• Experience with Kubernetes and Google Cloud Platform (GCP).
• Knowledge of model optimization techniques such as quantization and distillation.
• Familiarity with FastAPI and message brokers.
• 5+ years of professional experience.

Preferred Skills

• Experience with edge deployment strategies.
• Background in computer vision research or production deployment.

Key Skills

Education

Any Gradute