Senior ML Engineer - Model Optimization

Department: Engineering

Employment Type: Full Time

Location: Paris - Île-de-France

Description

Are you eager to work on large-scale, production-grade automotive perception with multi-sensor radar-centric fusion? Would you enjoy designing and optimizing state-of-the-art perception modules to be deployed across diverse edge devices aimed at series production? At Zendar, we have developed a robust infrastructure to collect and process millions of multi-sensor data points from diverse locations worldwide. We believe radar can achieve generalization with a fraction of the data and processing power required by camera-based perception models.

Your Role

Our current ML team is located in Berkeley, CA. You will be one of the first ML hires in our Paris office, with significant potential for growth, and you'll play a foundational role in building and shaping our Europe ML team as we continue to invest in its expansion over time. This is a unique opportunity to drive impact while staying closely connected to our US team. This role is ideal for an ML engineer who is passionate to work on model optimization while remaining open to working across all aspects of the ML and perception pipeline, including model design, data collection and preprocessing, as well as model testing and evaluation.
You will work closely with the perception team to shape our perception module for future production series, while also collaborating with chip designers to influence the development of compute architectures that align with our pipeline’s requirements. As the key expert on edge deployment, you will also work closely with our product team and external partners to bring our solution to market.

What We Look For

• Experience optimizing deep neural networks for real-time performance.
• Proficiency in modern Python and C++.
• Familiarity with model quantization, quantized aware training, NAS and model pruning, and other techniques for efficient deployment on edge devices
• Experience in training, testing, and verifying optimized neural network models
• Deep understanding of challenges in machine learning pipeline design such as data collection and processing, model test and evaluation
• Proficiency in Python
• Familiarity with professional software development tools, such as source control (git), unit testing, and profiling
• Strong communication skills and proven ability to collaborate effectively across function

Bonus Points

• Strong understanding of embedded systems constraints, including power efficiency, memory management, and real-time processing requirements
• Expertise on applying machine learning to perception problems such as segmentation, object detection and tracking
• Experience in writing custom CUDA kernels for optimized performance on GPU-based platforms.

What We Offer

• Opportunity to make an impact at a young, venture-backed company in an emerging market
• Competitive salary
• Lunch allowance, Carte Navigo and free snacks in the office
  
  

Zendar is committed to creating a diverse environment where talented people come to do their best work. We are proud to be an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.