Senior Staff Engineer — Autonomous Driving Planning

Lucid Motors

Newark (CA)

On-site

USD 210,000 - 420,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Lucid equity program

Discretionary annual cash incentive

Onsite work five days per week in San?

Job summary

Lucid Motors in Newark, California is seeking an experienced senior autonomy software engineer to advance trajectory optimization and planning. You will design constraint-aware methods, scale the planning stack across vehicle platforms, and optimize CPU use with parallel and GPU acceleration.

You will lead technical discussions, document insights, and ensure production readiness across real vehicles. The role requires 10+ years in autonomous driving or robotics, strong C/C++ skills, and hands-on

Qualifications

M.S. or Ph.D. in Robotics, Control, Electrical Engineering, or a related field.
10+ years of software development experience in autonomous driving, ADAS, or robotics focusing on large-scale data and real-time systems.
Strong C/C++ programming skills and understanding of software engineering design principles and best practices.
Experience delivering ADAS or autonomous-driving features through requirements analysis, architecture and design, implementation, unit testing, feature tuning, SIL/HIL validation, and in-vehicle deployment.
Hands-on experience integrating software on embedded platforms such as NVIDIA Xavier/Orin and Infineon Aurix.
Ability to build reliable production-grade systems, large-scale architectures, evaluation pipelines, and performance-optimized models.
Leadership experience.
Preferred qualifications include ML-based planning, GPU or parallel computing for planning, and production deployment in real vehicles.

Responsibilities

Develop trajectory optimization algorithms, including iLQR- and MPC-based approaches, for low-speed autonomous driving scenarios.
Design constraint-aware optimization methods and improve local planners to generate control-friendly trajectories.
Refactor and scale planning-stack architecture for maintainability, extensibility, and operation across scenarios and vehicle platforms.
Optimize CPU usage and investigate parallel and GPU acceleration opportunities.
Debug curvature discontinuities, velocity and trajectory mismatches, and edge-case steering behavior using simulation, vehicle logs, multi-scenario testing, and benchmarking.
Prototype and evaluate learned models, barrier functions, and ML-based planning approaches for production viability.
Drive technical discussions, document algorithm insights, support knowledge transfer, and track work in Jira.