Machine Learning Engineer - Model Optimization

Job description

We are seeking experienced ML engineers to optimize and deploy machine learning models on heterogeneous embedded computing platforms. You will work at the intersection of machine learning, compilers, runtime systems, and computer architecture, helping bridge the gap between models developed by researchers and highly optimized implementations running on production hardware. A major focus of this role is understanding the trade-offs between model quality and computational efficiency. You will work closely with machine learning researchers to develop and evaluate hardware-aware model architectures, identify computational bottlenecks, and explore architectural changes that improve latency, throughput and memory usage while maintaining model quality. The ideal candidate enjoys understanding both neural network architectures and the hardware on which they execute, and is interested in techniques such as hardware-aware neural architecture search, model scaling, quantization, mixed-precision inference, and model compression. It is an exciting opportunity to tackle real-world challenges in bringing algorithms developed in the lab to vehicles operating in diverse physical environments. About Zendar: Zendar builds a radar-centric autonomy stack which makes any vehicle - from cars to robots - autonomous in any environment. With our deep radar DNA, we have architected our solution to put RF sensing at the core of all perception. The result is a system that handles long range, high speeds, and bad weather not as edge cases but as a core strength of the autonomy stack. Because radars naturally measure both 3D position and velocity for every object in the environment, radar-centric autonomy is extremely compute- and data-efficient. Our autonomous vehicle needs only a few thousand dollars of hardware to make it completely autonomous, making this the cheapest way to build an autonomous vehicle by far. See a demo of Zendar’s foundational RF perception and driving functions To develop this capability we had to build the entire stack in house - from radar sensor hardware to signal processing to multi-modal perception foundation models and path and trajectory planning. As part of a small team, you will have a front-row seat to seeing how a complete autonomy stack is architected and how your engineering decisions improve the ability to navigate autonomously in the rear world. Although AI is central to what we build, our hiring process is intentionally human: every resume is reviewed by a real person. Please submit your resume in English. Your Role: We are seeking experienced ML engineers to optimize and deploy machine learning models on heterogeneous embedded computing platforms. You will work at the intersection of machine learning, compilers, runtime systems, and computer architecture, helping bridge the gap between models developed by researchers and highly optimized implementations running on production hardware. A major focus of this role is understanding the trade-offs between model quality and computational efficiency. You will work closely with machine learning researchers to develop and evaluate hardware-aware model architectures, identify computational bottlenecks, and explore architectural changes that improve latency, throughput and memory usage while maintaining model quality. The ideal candidate enjoys understanding both neural network architectures and the hardware on which they execute, and is interested in techniques such as hardware-aware neural architecture search, model scaling, quantization, mixed-precision inference, and model compression. It is an exciting opportunity to tackle real-world challenges in bringing algorithms developed in the lab to vehicles operating in diverse physical environments. Key Responsibilities: Profile and analyze machine learning models to identify computational, memory, and data-movement bottlenecks. Explore trade-offs between model output quality and computational cost, including latency, throughput, and memory footprint. Develop methodologies for hardware-aware model optimization and neural network architecture search, using real hardware measurements as optimization objectives. The target platform can include CPUs, GPUs, and dedicated AI accelerators. Apply model optimization techniques such as quantization, mixed-precision inference, distillation, and other model compression techniques. Perform analysis on the numerical differences introduced by these optimization techniques. Develop and maintain model export, benchmarking, and deployment pipelines across frameworks and inference runtimes such as PyTorch, ONNX, and TensorRT. Evaluate different deployment strategies and determine how models should be mapped onto heterogeneous processing units such as CPUs, GPUs, and dedicated AI accelerators. What We Look For: Strong understanding of machine learning and deep neural network architectures with hands-on experience developing machine learning models using frameworks such as PyTorch. Proficiency programming in python Experience analyzing the computational characteristics of neural networks and understanding how model architecture affects inference performance. Familiarity with techniques such as model architecture search, model scaling, quantization, mixed-precision inference, knowledge distillation, or other model compression methods. Experience with machine learning inference and deployment technologies such as ONNX, TensorRT, or similar frameworks. Ability to reason across different layers of the ML deployment stack, from model architecture and computational graphs to inference runtimes and hardware execution. Familiarity with professional software development practices and tools, including Git, unit testing, debugging, and profiling. Strong communication skills and the ability to work effectively across machine learning research, embedded software, and product engineering teams. Fluent in English and French, both written and spoken. Bonus Points: Proficiency with modern C++ Familiarity with CUDA/OpenCL Experience deploying machine learning models in embedded systems Experience mentoring team members on software development and best practices What We Offer: Opportunity to make an impact at a young, venture-backed company in an emerging market Competitive salary ranging from €75,000 to €90,000 annually depending on experience and equity Hybrid work model: in office 3 days per week (Monday, Tuesday, Thursday), the rest… work from wherever! Modern Workspace: Fully equipped, modern office in the heart of Paris Transportation/Commute: Commuter benefits (partial reimbursement for public transport, where applicable) Subsidized meal vouchers (tickets restaurant) Wellness Pass (ex Gymlib) 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.