Vacancy catalog
OLD

Long-running vacancy

This listing is older than 30 days but its source has not removed it. Verify availability on the original company page before applying.

Svitla Systems
Open role>1 month

C++ ENGINEER WITH COMPUTER VISION

Work model
Remote
Experience
Not specified
Employment
Full Time
Compensation
Not disclosed
Technology signal
11 tags

Technology context

11

Parsed from the vacancy text; ordered by relevance to this role.

Full listing

Role description

Svitla Systems Inc. is looking for a Senior C++ Engineer with Computer Vision for a full-time position (40 hours per week) in Europe . Our client is an American mobile computing company.

You will bridge the gap between high-level machine learning research and high-performance production environments. Also, you will be responsible for building robust SDKs, automating deployment pipelines, and ensuring the models run efficiently across a diverse hardware landscape, from edge SoCs to powerful cloud GPUs.

  • Bachelor's or master's degree in Computer Science, Electronic Engineering, or related technical field.
  • Deep understanding of C++14/17/20, including STL, memory management, and multi-threading.
  • Expertise in writing 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.
  • Understanding of deep learning fundamentals (CNNs, Transformers, Object Detection).
  • Knowledge of model conversion and quantization (i.e., PTQ, QAT).
  • 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 in Python to streamline the model testing and deployment lifecycle.