Senior ML Engineer – Edge Model Deployment (onsite)

About Zendar

Zendar develops high-resolution radar imaging systems that enable next-generation safety features and driver-assistance technology that is reliable in all conditions and at sufficiently long range for high speed driving. Zendar has pioneered software-defined radar technology which fuses data streams from multiple sensors to build a more accurate scene and utilizes artificial intelligence models that interpret RF spectrum to understand the environment.

Zendar is headquartered in Berkeley, CA and has additional engineering offices in Germany and France.

Zendar has a diverse and dynamic team of electrical, mechanical, RF, algorithms and software engineers with a deep background in sensing technology. Backed by leading VCs and automotive Tier-1s, Zendar has raised more than $50M in funding and has established strong partnerships with industry leaders. Our team has more than doubled in number over the last year as our technology has gained traction.

Your Role

At Zendar, we’ve developed a robust semantic spectrum perception pipeline using millions of training samples, achieving high-performance object detection that positions radar as a key sensor for safety and autonomy in mass-market vehicles. Our models are designed for deployment across diverse edge devices aimed at series production.

In this role, you will be a core member of the machine learning and perception team, focusing on optimizing and deploying our machine learning models on targeted edge compute platforms. Key responsibilities include:

• Deeply understanding the capabilities, TOPS, and memory bandwidth of each target platform.
• Designing or adapting models to align with the hardware specifications and supported operations of the edge device.
• Training and testing models to ensure they meet all runtime and performance requirements.

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

• 3+ years of experience in optimizing deep neural networks and deploying them across diverse compute platforms, including but not limited to Qualcomm, and NXP.
• Proficiency in modern Python and C++.
• Expertise in designing and optimizing neural network models for edge deployment.
• 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.
• Proficient in at least one major deep learning framework (e.g., PyTorch, TensorFlow).
• Strong communication skills and proven ability to collaborate effectively across functions.

Bonus Points

• Experience in writing custom CUDA kernels for optimized performance on GPU-based platforms.
• Hands-on experience applying machine learning to perception problems
• Strong understanding of embedded systems constraints, including power efficiency, memory management, and real-time processing requirements.
• Background in algorithm optimization for resource-constrained environments

What We Offer

• Opportunity to make an impact at a young, venture-backed company in an emerging market
• Competitive salary ranging from $145-190k annually depending on experience
• Performance based Bonus
• Benefits including medical, dental, and vision insurance, 401k plan, flexible PTO, and equity
• Daily catered lunch and a stocked fridge (when working in the Berkeley, CA 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.

Zendar participates in E-Verify.