Senior Machine Learning Research Engineer

Zendar is looking for a Senior Machine Learning Research Engineer (Multi-Sensor Fusion Perception & Foundation Models) to join our Berkeley office. Zendar develops one of the best 360-degree radar-based vehicular perception systems for automotive. We’re now expanding our capabilities to deliver full-scene perception outputs using early fusion of camera and radar, and scaling these technologies across both the automotive and robotics industries. We are not bogged down by legacy systems, and by joining us you’ll have the opportunity to define and own a next-generation perception stack that enables reliable autonomy at scale.

Autonomous vehicles need to be able to understand the world around them not only in bright daylight, but also at night, when it is foggy or rainy, or when the sun is shining right in your face. At Zendar, we make this possible by developing the highest-resolution, most information-rich radar in the world.

What makes radar powerful - its long wavelength which makes it robust to all sorts of weather and lighting conditions - also makes it really challenging to work with. We have used our deep understanding of radar physics to build radar perception models that bring a rich and complete understanding of the environment around the AV from free space to object detections to road structure. Check out what our technology can do here - all produced with only radar information, no camera and no lidar!

Zendar has a diverse and dynamic team of hardware, machine learning, signal processing and software engineers with a deep background in sensing technology. We have a global team of 60, distributed across our sites in Berkeley, Lindau (Germany), and Paris.

Zendar is backed by Tier-1 VCs, has raised more than $50M in funding and has established strong partnerships with industry leaders.

Zendar’s Semantic Spectrum perception technology extracts a rich scene understanding from radar sensing. Our next goal is to build a foundation-model-driven perception stack that fuses streaming camera and radar to produce full perception outputs that are robust enough for real-world autonomy: occupancy/free-space (e.g., occupancy grid), object detection and tracking, lane line and road structure estimation, and the interfaces required to make these outputs actionable for downstream systems.We are seeking an experienced Senior ML Engineer to design, implement, and drive the architecture of these models end-to-end, including training from scratch on large-scale datasets (not just fine-tuning), defining evaluation and long-tail validation, and partnering with platform and product teams to ensure successful deployment in real-time systems.This is an ideal position for an engineer who enjoys owning hard technical problems, making rigorous tradeoffs, and building systems that work reliably in the messy long tail of the real world.In this role you will have close communication and collaboration with platform, embedded, and robotics teams. You will work with our real-world dataset of tens of thousands of kilometers collected in multiple continents and geographies, and you will have opportunities to validate results on real vehicles.

Own architecture and technical strategy for multi-sensor perception models, including explicit tradeoffs (why approach A vs B), risks, validation plans, and timelines.Build foundation-scale / transformer-based perception models trained from scratch on large-scale multi-modal driving datasets (not limited to fine-tuning).Develop fusion architectures for streaming multi-sensor inputs (camera/radar/lidar), with early fusion and temporal fusion; align training objectives to real-world reliability targets.Deliver production-ready models for:Occupancy / free-space / dynamic occupancy (full-scene understanding)3D Object detection and trackingLane line / road structure estimationDrive long-tail reliability (e.g., toward “four nines” behavior in defined conditions)Partner with platform/embedded teams to ensure models meet real-time constraints (latency, memory, throughput) and integrate cleanly via stable interfaces for downstream consumers.

• Deep expertise in deep learning for perception, especially transformer-based architectures, temporal modeling, and multi-modal learning.
• Proficiency with Python and a major deep learning framework (e.g., PyTorch, TensorFlow)
• 5+ years (or having a PhD) experience designing and implementing ML systems, with demonstrated ownership of research/production outcomes.
• Demonstrated experience training large models from scratch (not only fine-tuning)
• Strong experience with multi-sensor fusion (camera/radar/lidar) and real-world sensor
• Strong understanding of the end-to-end perception stack and downstream needs (interfaces, uncertainty, temporal stability, failure modes).
• Ability to lead architectural discussions: articulate tradeoffs, quantify risks/benefits, and set realistic milestones and timelines.

• PhD in a relevant field (Machine Learning, Computer Vision, Robotics) preferred.
• Experience with foundation models for autonomy and robotics, including multi-modal pretraining, self-supervised learning, and scaling laws / model scaling strategies.
• Experience with transfusion-style or related fusion paradigms (transformer-based fusion across modalities and time), including building from first principles.
• Experience with BEV-centric perception, 3D detection, occupancy networks, tracking, and streaming inference.

What We Offer:

• Opportunity to make an impact at a young, venture-backed company in an emerging market
• Competitive salary ranging from $140,000 to $190,000 annually depending on experience
• Performance based Bonus
• Benefits including medical, dental, and vision insurance, flexible PTO, and equity
• Hybrid work model: in office 3 days per week from Tuesday to Thursday, the rest… work from wherever!
• Daily catered lunch and a stocked fridge (when working out of 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