Senior Software Engineer - 3D Perception

Motional is a driverless technology company making autonomous vehicles a safe, reliable, and accessible reality. As a Senior Software Engineer - 3D Perception, you will design and implement teacher-student model frameworks for multimodal sensor data, optimize model deployment for real-time inference, and collaborate with various teams to translate research into scalable engineering solutions.

Responsibilities:

• Architect and Train Distilled Models: Design and implement teacher-student model frameworks for multimodal sensor data. Develop training pipelines for knowledge distillation. Ensure student models maintain high accuracy while drastically reducing inference latency and memory footprint
• Reinforcement Learning for Data Discover: Build RL-based policy learning and reasoning systems for autonomous driving applications. Implement and scale RL training workflows (e.g., PPO, DQN, actor-critic methods) for simulation and real-world interaction. Explore reward shaping, environment modeling, and multi-agent RL where applicable
• Optimize Model Deployment for Real-Time Inference: Collaborate with backend engineers to deploy distilled and RL models into production. Optimize for latency, throughput, and hardware efficiency across GPU/CPU clusters. Implement model versioning, A/B testing, and monitoring for performance regressions
• Research and Integrate Agentic Systems: Explore and prototype agentic workflows for autonomous reasoning, chain-of-thought prompting, and goal-directed behavior. Integrate such systems into our broader autonomy stack as experimental or production components
• Drive Production Reliability: Establish patterns for graceful degradation, fault tolerance, and cost optimization. Operate Omnitag as a mission-critical data platform serving the entire ML organization, with a focus on reliability, debuggability, and operational excellence
• Mentor and Collaborate: Work closely with ML scientists, data engineers, and autonomy teams to translate research advances into scalable engineering solutions. Guide junior engineers in best practices for model training, evaluation, and deployment