Senior Machine Learning Engineer (Nvidia DeepStream, Ukraine) #14645

Purpose Of The Job

At Capgemini Engineering, the world leader in engineering services, we bring together a global team of engineers, scientists, and architects to help the world’s most innovative companies unleash their potential. From autonomous cars to life-saving robots, our digital and software technology experts think outside the box as they provide unique R&D and engineering services across all industries. Join us for a career full of opportunities. Where you can make a difference. Where no two days are the same. Our client is a mission-driven organization. They are comprised of employees who are passionate about keeping people safe. Simply stated, they put people first, whether it’s protecting those visiting the places where people gather or through the support and development of our own employees. Our product is the world’s first and only touchless security screening solution that meets all of the post-pandemic security screening requirements. It is up to ten times faster and far more effective than last generation products because it uses new sensor technology and artificial intelligence. Unlike traditional metal detectors, it’s powered by AI Software Platform enabling the system to spot weapons while ignoring harmless personal items. It keeps high volume entrances flowing by reliably detecting guns and other weapons as visitors walk through at a natural pace while carrying their phones and bags. We are looking for an individual that can help optimize and deploy trained models onto edge devices for real time video analysis applications, focusing on performance tuning.

Main Tasks And Responsibilities

Optimize and Deploy Models: Deploy trained models onto edge devices for real-time video analysis, ensuring optimal performance

Performance Tuning: Profile and tune models using Nvidia DeepStream/GStreamer for improved speed and reduced latency

Python Development: Create and maintain Python applications for model integration and deployment

Utilize Optimization Tools: Use TorchScript/TensorRT for model optimization on Nvidia Jetson/Orin devices

Implement Hardware Acceleration: Enhance model inference performance through hardware acceleration techniques

Containerization and Version Control: Manage deployments with Docker and version control using Git

Collaborate and Document: Work with cross-functional teams and document best practices and performance metrics

Education, Skills And Experience

MUST HAVE:

Be a strong Python Programmer

Have experience with Nvidia DeepStream/GStreamer

Have experience with TorchScript/TensorRT for model optimization

Have deployed models on the edge, e.g. Nvidia Jetson/Orin devices

Have experience with hardware acceleration and performance profiling

Familiar with Docker, Git and Linux

Would Be a Plus

Experience with AWS EC2/ECR for containerization and model deployment

Experience with model versioning and management tools (e.g., DVC, MLflow)

Experience with Post-training Quantization and Quantization Aware Training