Deep Learning Optimization Engineer

Eindhoven, Netherlands

NavInfo Europe BV logo
NavInfo Europe BV
Apply now Apply later

Posted 3 weeks ago

Our mission

Navinfo is the largest Digital Map Provider in China and third largest in the world.
Our core competence is the extraction of map related features from images by intense use of Deep Learning and Computer Vision. Part of our mission is to evaluate latest technology for use in map automation and support business units with the integration of this technology into a production environment.


Your responsibility is the design, implementation and maintenance of Deep Learning based software. This mainly includes retrofitting the models, designs, code and related tools with optimized machine learning frameworks for final delivery customers.

Work Environment

You will join our multi-cultural team of Deep Learning/Computer Vision engineers within the ‘Advanced Research Lab’ (ARL) department.

You will work with up to date Deep Learning technology in a team of highly skilled professionals with a passion for parallel programming and GPGPU based optimizations for neural networks. Being a team player with excellent communication skills is a key requirement for us. As English is our working language your level should be B2 or higher.

We support use cases from Deep Learning object detection in a real-time in-car scenario to server based Deep Learning Scene Segmentation. See our YouTube channel


Core Tasks

  • Provide support to a team of C++ developers from a DL perspective in order to improve neural network inference and optimization
  • Help in integration of optimized code to edge devices
  • Develop and maintain tools in Deep Learning related processes
  • Maintain clear and effective communication with the team and other team as necessary

  • A MSc or BSc degree, preferably in machine learning, computer vision, computer science, mathematics or physics
  • Strong software engineering skills in both C++ and Python
  • Experience with parallel computing, especially TensorRT, CudNN and ONNX
  • Experience with GPU acceleration for AI is a major plus
  • Experience with deploying AI models on embedded devices such as TX2
  • You have a working know how of object detection, segmentation, classification and re-identification
  • You are familiar with scientific computing and systems and have quick model prototyping experience in TensorFlow/PyTorch with GPUs
  • Good knowledge of Deep Learning
  • You have experience building production-scale data pipelines in Python.
  • You preferably have professional experience in software engineering for the full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations
  • Good software engineering skills grounded in principled best practices
  • Computer Science fundamentals in algorithm design, complexity analysis, problem solving and diagnosis

    We offer:

    A competitive salary (based on a 40-hour week), consistent with your level of education and experience

    An initial one-year contract with the prospect of an indefinite contract

    A 8% holiday allowance annually

    25 vacation days, 5 compensation days

    Flexible working hours

    Extensive training opportunities

    Pension and health insurance participation options

    A fast moving, innovative and international diverse working environment

    • If you feel you fit the description and you are interested in working within a fast growing, international and innovative organisation with a solid customer base, then please send your CV to or apply via the application button below. You can expect a challenging job with a market conforming employment package. For more information please contact the HRM department +31 40-711 35 56, Luchthavenweg 34, 5657 EB Eindhoven.

Job tags: AI Computer Vision Deep Learning Engineering GPU Machine Learning Python PyTorch Research TensorFlow