C++ Computer Vision AI Engineer, Medior

We are seeking a skilled and motivated Computer Vision Engineer to join our team. In this role, you will bridge the gap between high-level machine learning research and high-performance production environments. You will be responsible for building robust SDKs, automating deployment pipelines, and ensuring our models run efficiently across a diverse hardware landscape, from edge SoCs to powerful cloud GPUs. 

• SDK Development (C++) 
  Design, develop, and maintain high-performance software development kits (SDKs) to expose computer vision capabilities to end-users and internal products. 

• Model Deployment and Integration 
  Port, convert, and deploy machine learning models across various hardware targets, including Qualcomm SoCs, Intel CPUs, and NVIDIA GPUs. 

• Performance Optimization 
  Use hardware-specific toolkits to optimize model throughput without sacrificing accuracy. 

• Evaluation & Benchmarking 
  Conduct rigorous testing and evaluation of models on target hardware to ensure performance metrics meet expectations. 

• Automation 
  Build and maintain automation scripts and CI/CD pipelines using Python to streamline the model testing and deployment life cycle. 

• Deep understanding of C++14/17/20, including STL, memory management, and multi-threading.
• Strong ability to write clean, maintainable Python for automation, and data processing.
• Hands-on experience with at least one of the following frameworks:
  • SNPE/QNN (Qualcomm)
  • OpenVino (Intel)
  • TensorRT (Nvidia)
  • TensorFlow Lite
• Familiarity with Docker for creating consistent development and deployment environments.

Bonus:

• Understanding Deep Learning fundamentals (CNNs, Transformers, Object Detection).
• Experience with model conversion and quantization (i.e. PTQ, QAT).