Software Engineer, Autonomous Vehicles (Motion Planning)
- Role
- Backend
- Experience
- Senior
- Employment
- Full-time
- Company size
- Startup
Open to US only. Set where you work from to check your eligibility.
No BS summary
Senior software engineer for autonomous vehicle motion planning, remote in the US. Needs strong C++ for real-time systems, Python, planning algorithms, vehicle dynamics, and ROS/ROS2 or comparable autonomous middleware. Autonomous vehicle experience is not required, but robotics/CS/EE graduate-level background or equivalent industry experience is required.
Core skills
Required skills
Optional skills
We help make autonomous technologies more efficient, safer, and accessible.
Helm. Our "Deep Teaching" methodology is uniquely data and capital efficient, allowing us to surpass traditional approaches. Our unsupervised learning software can train neural networks for L2/L3 autonomy, which drastically reduces the need for human annotation and is hardware-agnostic.
We are looking for versatile engineers to shape core components of the next generation of the Helm. No prior experience in autonomous vehicles is required—we prioritize deep expertise in backend systems and a proven track record in high-impact software engineering. In this senior role, you will design, implement, and test safe, efficient, and reliable vehicle software/hardware systems, collaborate with sensor and compute vendors, partner with Helm.
You will:
- Architect core behavior planning: Own the logic and decision frameworks that guide the vehicle through complex maneuvers (like unprotected turns, dynamic merges, and yielding).
- Optimize trajectories: Develop robust trajectory generation systems that perfectly balance safety, passenger comfort, and vehicle progress.
- Ensure verifiable safety: Translate complex traffic rules and operational design domain (ODD) constraints into interpretable, highly safe planning behaviors.
- Solve the long-tail: Tackle exciting, real-world edge cases, from unpredictable pedestrians and occlusions to complex construction zones.
- Drive cross-functional integration: Collaborate closely to seamlessly connect your planner with perception, prediction, localization, and control modules.
- Test and validate: Prove out your solutions through rigorous scenario-based simulations, closed-course trials, and live on-road testing.
- Optimize for real-time: Deliver robust, highly deterministic performance tailored for embedded automotive hardware.
You have:
- MS/PhD in robotics, Computer science, Electrical Engineering, or equivalent industry experience.
- Solid C++ for robust, real-time systems, paired with Python for tooling and data analysis.
- Deep familiarity with both planning algorithms (search, sampling and optimization-based) and complex decision architectures (like FSMs and behavior trees).
- A solid grasp of vehicle kinematics and dynamics to ensure safe, smooth, and realistic motion profiles.
- Hands-on experience with ROS/ROS2 or comparable autonomous middleware.
The following are not required but a plus:
- Experience shipping a planner on public roads and analyzing real-world disengagement data.
- Hands-on experience with tools like CARLA or custom in-house scenario frameworks.
We offer:
- Competitive health insurance options
- 401K plan management
- Remote-friendly and flexible team culture
- Free lunch and fully-stocked kitchen in our South Bay office
- Additional perks: monthly wellness stipend, office set up allowance, company retreats, and more to come as we scale
- The opportunity to work on one of the most interesting, impactful problems of the decade
Helm. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status.
Any unsolicited resumes/candidate profiles submitted through our website or to personal email accounts of employees of Helm.
What you'll do
- Architect core behavior planning and own the logic and decision frameworks that guide the vehicle through complex maneuvers such as unprotected turns, dynamic merges, and yielding.
- Develop robust trajectory generation systems that balance safety, passenger comfort, and vehicle progress.
- Translate complex traffic rules and operational design domain constraints into interpretable, highly safe planning behaviors.
- Tackle real-world edge cases such as unpredictable pedestrians, occlusions, and complex construction zones.
- Collaborate to connect the planner with perception, prediction, localization, and control modules.
- Test and validate solutions through scenario-based simulations, closed-course trials, and live on-road testing.
- Deliver robust, deterministic real-time performance tailored for embedded automotive hardware.
- Design, implement, and test safe, efficient, and reliable vehicle software/hardware systems.
- Collaborate with sensor and compute vendors.
- Partner with Helm.ai’s AI teams.
- Work with customers to advance highway and urban autonomous driving capabilities.
What they require
- MS/PhD in robotics, Computer Science, Electrical Engineering, or equivalent industry experience.
- Solid C++ for robust, real-time systems, paired with Python for tooling and data analysis.
- Deep familiarity with planning algorithms, including search, sampling, and optimization-based algorithms.
- Deep familiarity with complex decision architectures such as FSMs and behavior trees.
- Solid grasp of vehicle kinematics and dynamics to ensure safe, smooth, and realistic motion profiles.
- Hands-on experience with ROS/ROS2 or comparable autonomous middleware.
- Preferred: Experience shipping a planner on public roads and analyzing real-world disengagement data.
Benefits
- Competitive health insurance options.
- 401K plan management.
- Remote-friendly and flexible team culture.
- Free lunch and fully-stocked kitchen in South Bay office.
- Monthly wellness stipend.
- Office set up allowance.
- Company retreats.
- Opportunity to work on one of the most interesting, impactful problems of the decade.
Helm.ai builds AI software for autonomous driving and robotics. Its Deep Teaching methodology is data and capital efficient, using unsupervised learning software to train neural networks without human annotation or simulation, and it works with large automotive manufacturers.