Description:

Serve Robotics is seeking a Software Engineer specializing in Machine Learning to develop dependable and proficient sidewalk autonomy software.
The role involves identifying, implementing, and fine-tuning foundational vision grounding models for auto-labeling large amounts of data for various use-cases.
Responsibilities include training and deploying learning-based perception models for on-robot perception systems, optimizing machine learning models for embedded hardware platforms, and developing high-performance custom kernels using CUDA.
The engineer will work closely with ML infrastructure engineers to monitor model performance and resolve performance bottlenecks.
The position requires producing high-quality code, participating in code reviews, and sharing knowledge with the team.

Requirements:

A Master’s degree in Computer Science and at least 2 years of industry experience focused on Machine Learning, Deep Learning, Robotics, or a similar technical field, or equivalent practical experience is required.
Candidates must have 2+ years of production-grade coding experience in C++, Python, and CUDA programming.
Experience with edge-device perception stack deployment and familiarity with NVIDIA software libraries such as CUDA or TensorRT is necessary.
A fundamental understanding of computer vision, machine learning, and deep learning concepts is essential.
Candidates should have experience optimizing ML performance on hardware, ideally with embedded platforms or autonomous systems.
Experience working with multiple sensors such as Lidar, Mono/Stereo cameras, and IMU is required.
Strong communication skills are a must.

Serve Robotics offers a collaborative and respectful work environment with a diverse team of tech industry veterans.
Employees will have the opportunity to work on innovative projects that leverage robotics, machine learning, and computer vision to solve real-world problems.
The company promotes professional growth and knowledge sharing among team members through code reviews and collaborative problem-solving.
The position is fully remote, providing flexibility in work arrangements.