Sr. Machine Learning Engineer, Prediction

Position Overview

• Location Type: Remote
• Job Type: Full-Time
• Salary: $175K - $230K

Serve Robotics is reimagining urban logistics with our personable sidewalk robots. We’re building the future of delivery, taking it away from congested streets and benefiting local businesses. We’re looking for a driven engineer to join our prediction pipeline team, where you’ll refine agent prediction models using point cloud (LiDAR/Radar) and camera data. You’ll also lead efforts to incorporate a geometric-based module for redundancy, ensuring robust and dependable performance.

Requirements

• Master’s degree in Computer Science, Robotics, Electrical Engineering, or a related field.
• 3+ years of industry experience in building perception and prediction modules for robotics/AV stacks.
• Hands-on experience with machine learning frameworks (TensorFlow, PyTorch, etc.).
• Exposure to state-of-the-art research or publications in perception and prediction approaches.
• Strong background in sensor fusion (especially LiDAR and camera) and computer vision related to 3D perception and spatio-temporal tracking.
• Proven track record of building ML pipelines and deploying models in production.

Responsibilities

• Develop and maintain prediction pipelines that integrate both LiDAR and camera inputs and integrates with the planner.
• Research and implement state-of-the-art algorithms for 3D perception, tracking, and prediction.
• Conduct ablation studies and parameter sweeps using simulations to thoroughly validate safety and trust implications in predicting high-risk factor object semantics accurately.
• Curate diverse, real-world datasets for tracking and prediction pipeline to train and evaluate new models.
• Analyze performance metrics and optimize models for reliability, efficiency, and deployability.
• Collaborate with Behavior Planning to define SLAs and integrate prediction outputs; partner cross-functionally to evaluate new sensors’ impact on prediction performance.

Company Information

• At Serve Robotics: We are tech industry veterans in software, hardware, and design, pooling our skills to build the future we want to live in. We are solving real-world problems leveraging robotics, machine learning, and computer vision, with a mindful eye towards the end-to-end user experience. Our team is agile, diverse, and driven. We believe that the best way to solve complicated dynamic problems is collaboratively and respectfully. We are committed to developing reliable, cutting-edge sidewalk autonomy software.