ML Performance Engineer - Remote

Overview

At Serve Robotics, we’re reimagining how things move in cities. Our personable sidewalk robot is our vision for the future. It’s designed to take deliveries away from congested streets, make deliveries available to more people, and benefit local businesses.

The Serve fleet has been delighting merchants, customers, and pedestrians along the way in Los Angeles while doing commercial deliveries. We’re looking for talented individuals who will grow robotic deliveries from surprising novelty to efficient ubiquity.

In Short

• Own the full lifecycle of ML model deployment on robots.
• Convert, optimize, and integrate trained models for Jetson platforms.
• Develop and optimize CUDA kernels and pipelines for model inference.
• Profile and benchmark existing ML workloads.
• Identify and remove compute and memory bottlenecks.
• Design strategies for model compression techniques.
• Ensure models are robust to resource constraints.
• Manage memory layout and scheduling for optimized usage.
• Build benchmarking pipelines for performance evaluation.
• Collaborate with QA and systems teams for model validation.

Requirements

• Bachelor’s degree in Computer Science, Robotics, or equivalent.
• 3+ years experience in deploying ML models on embedded platforms.
• 2+ years of experience with CUDA and TensorRT.
• Proficient in Python and C++.
• Experience with NVIDIA Jetson and edge inference tools.
• Familiarity with model conversion workflows.

Benefits

• Work with a diverse and agile team.
• Opportunity to influence real-world robotics solutions.
• Collaborative work environment.
• Engage in cutting-edge technology development.