In this production engineering role, you will spend meaningful time on failure analysis, long-tail scenarios, and the gap between offline metrics and on-road behavior. If you are passionate about applying cutting-edge ML to solve high-stakes robotics challenges, we want to hear from you.
What You’ll Do
Design, train, and deploy models for behavioral prediction and motion planning that run on vehicles in real traffic
Model multi-agent interaction and temporal dynamics — how a merge, an unprotected left, or an occluded pedestrian actually unfolds
Own the metrics: build evaluation frameworks that correlate with real on-road safety and performance, not just offline loss
Diagnose long-tail failures from real driving logs and close the loop back into training data and model design
Optimize trained models for real-time inference under strict latency, memory, and compute constraints on embedded hardware
Build and maintain data pipelines that process, clean, and label large-scale vehicle sensor and simulation datasets
What You’ll Need
Domain experience (required)
Hands-on experience with at least one of: behavioral or trajectory prediction, motion planning, decision-making under uncertainty, or closely adjacent autonomy work (navigation, SLAM, control, or perception-for-planning) for autonomous vehicles, mobile robots, drones, or comparable physical systems
Experience deploying machine learning to real hardware operating in the physical world, under real-time or resource constraints. Simulation-only or offline-only experience does not meet this bar.
Engineering (required)
Strong Python and production experience with a modern deep learning framework (PyTorch, TensorFlow, or JAX)
Proficiency in C++ (or Rust) for performance-critical inference and integration code
Demonstrated ownership of a system from prototype through deployment, including debugging it after it shipped
How We Evaluate
We weight what you have actually built and shipped far more heavily than credentials. We regularly hire people without advanced degrees and without prior autonomous-vehicle experience. What we look for is specific, verifiable engineering work systems you built, constraints you worked under, and failures you diagnosed and fixed
#LI-MS1
Candidates are required to be authorized to work in the U.S. The employer is not offering relocation, sponsorship, and remote work options are not available.
Avride is an equal opportunity employer and committed to providing reasonable accommodations to qualified applicants and employees with disabilities to ensure they have equal access to employment opportunities. Avride complies with the Americans with Disabilities Act (ADA), if you need a reasonable accommodation to assist with the application or hiring process, or to perform the essential functions of a job, please email jobs@avride.ai.
