Senior ML Engineer – Robotics – United States – Remote

Serve Robotics is dedicated to developing reliable and efficient sidewalk autonomy systems, with a focus on perception, prediction, and other innovative machine learning tasks. Our Perception & Prediction team is looking for a passionate individual who can tackle complex technical challenges in sidewalk autonomy.

Key Responsibilities

• Develop foundational models for vision, language, and action that demonstrate strong reasoning and maneuvering capabilities, with expertise in transformer-based machine learning architectures.
• Design, train, and deploy perception models that support on-robot systems. These models should be capable of multi-modal learning, encompassing tasks such as segmentation, object detection, scene understanding, and tracking.
• Collaborate with ML infrastructure engineers to monitor and evaluate model performance, identifying and resolving performance bottlenecks.
• Work cross-functionally to understand real-world problems, define tasks, and integrate insights into machine learning solutions.
• Write high-quality code, participate in code reviews, and share knowledge across teams to maintain code excellence.
• Work with SQL queries and ETL logic for managing data ingestion.

Qualifications

• MS/PhD in Computer Science (or equivalent practical experience) with at least 5 years of industry experience in machine learning, deep learning, robotics, or a related field.
• 2+ years of experience in training and deploying machine learning models to production, with a focus on lifecycle management.
• Deep understanding of computer vision, machine learning, and deep learning fundamentals.
• Strong proficiency in C++ and Python for developing efficient and reliable software.
• Experience working with multiple sensors (Lidar, Mono/Stereo cameras, IMU, etc.).
• Strong communication and collaboration skills.

What Makes You Stand Out

• Publications in top conferences or journals, such as CVPR, NeurIPS, ICCV, TPAMI, TRO, etc.
• Experience tackling robotics and computer vision challenges in at least two of the following areas: multi-sensor fusion, object detection and tracking, 3D estimation, and embodied AI with transformer-based models.
• Familiarity with deploying perception stacks on edge devices, including experience with NVIDIA software libraries like CUDA or TensorRT.
• Contributions to open source projects.
• Experience with cloud platforms like GCP or AWS, as well as container technologies such as Kubernetes and Docker.

Hiring Locations

Currently, we are hiring residents of the US and Canada, including for remote positions.

About Us

Serve Robotics is the team behind the Postmates delivery robot, which successfully completed tens of thousands of deliveries in some of Los Angeles’ busiest neighborhoods. As an independent company, we are rapidly expanding our capabilities to deliver goods via robots designed to serve people.

We are proud to be an equal opportunity employer, considering all qualified applicants without regard to race, color, religion, national origin, age, sex, marital status, ancestry, disability, veteran status, gender identity, or sexual orientation.