Senior Software Engineer - Vehicle Motion Planning & Control

Zendar•Berkeley, CA

23d•$160,000 - $180,000•Hybrid

About The Position

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. 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 real world. Although AI is central to what we build, our hiring process is intentionally human: every résumé is reviewed by a real person.

Requirements

Ability to work from the office in Berkeley, CA, at least from Tuesday to Thursday
3+ years of software engineering experience, with production-quality coding skills in modern C++ and Python
Hands-on experience in motion planning, decision making, or vehicle controls (e.g., optimization-based planning, search methods, optimal control, MPC, probabilistic decision making) on autonomous vehicles, ADAS, or robotic systems
Solid foundation in linear algebra, geometry, statistics & probability, and vehicle dynamics
Experience taking features from design through real-world deployment — not just prototypes
Ability to break down complex, ambiguous problems into well-defined technical solutions
Somebody with solid opinions based on experience, yet open-minded and flexible to find the best solution for the situation

Nice To Haves

Experience deploying planning or control software on real vehicles (AV, ADAS features like ACC, AEB, lane keeping / lane changing)
Experience with real-time and embedded systems and RTOS
Experience with ML-based approaches to planning (imitation learning, RL, learned cost functions) alongside classical methods

Responsibilities

Design and Build the Motion Planning Stack: Develop trajectory planning and decision-making algorithms that produce safe, smooth, dynamically feasible motion in dynamic, uncertain environments — including scenarios with noisy or incomplete perception input.
Reason about interactions with other road users and translate desired driving behavior into algorithmic changes across the planning stack.
Develop Vehicle Control Software: Architect, implement, and validate control and estimation algorithms for the vehicle's longitudinal and lateral dynamics.
Write mission-critical, real-time C++ that runs on-vehicle and on embedded automotive compute.
Integrate with Perception and Platform: Work closely with our Perception and Software Platform teams to define clean interfaces between perception output, planning, and control.
Support driving-function demos on our vehicles, from bring-up through customer-facing runs.
Test, Measure, and Improve: Build simulation and analysis tooling in Python and C++ to evaluate planner and controller performance before code ever touches a vehicle.
Define metrics for driving quality and safety, extract insights from field data, and feed them back into development.
Contribute to failure and hazard analyses and implement safety mitigations in planning and control software.