Software Engineer, Machine Learning

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.

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.

Who We Are

We are tech industry veterans in software, hardware, and design who are 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, among other disciplines, 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.

What you'll be doing

Serve Robotics aims to develop dependable and proficient sidewalk autonomy software. We are looking for a cracked software engineer who understands AI fundamentals, industry experience in robotics or AV space, practical deep learning model training experience from a data-centric approach and has experience optimizing models to run in edge embedded hardware platforms.

Responsibilities

• Identify, implement and fine-tune foundational vision grounding models that can be used to auto label large amounts of data for perception, prediction and mapping use-cases.

• Train and deploy learning-based perception models using data-centric techniques for on-robot perception systems. Perception models should be able to do multi-modal learning capturing different semantics such as segmentation, object detection, scene understanding and tracking.

• Optimize and accelerate machine learning models for deployment on embedded hardware platforms. Profile and analyze model performance, identify bottlenecks, and implement solutions to improve computational efficiency and reduce latency

• Become an in-house expert in concepts knowledge distillation, quantization, model compression, and mixed-precision training.

• Develop high-performance custom kernels using CUDA, or other low-level programming tools to accelerate computations and implement efficient algorithms.

• Work with ML infrastructure engineers to assess and monitor model performance, analyze and resolve performance bottlenecks.

• Produce high-quality code for software development, participate in code reviews to ensure the quality of code, and share knowledge with the team.

Qualifications

• Master’s in Computer Science degree and 2+ years of industry experience with focus in ML/DL, Robotics, similar technical field of study, or equivalent practical experience

• Proficient software engineer with 2+ years of production grade coding experience with C++, Python, CUDA programming.

• Experience with edge-device perception stack deployment, experience with NVIDIA software libraries such as CUDA or TensorRT.

• Fundamental understanding of computer vision, machine learning and deep learning basic concepts.

• Experience pushing the boundaries of ML performance on hardware and has ideally worked on embedded platforms or autonomous systems before.

• Experience working with multiple sensors such as Lidar, Mono/Stereo cameras, IMU, etc.

• Strong communication skills.

What makes you standout

• Demonstrated proficiency in tackling robotics and computer vision challenges within at least two of the following domains: multi-sensor feature extraction and fusion, object detection and tracking, 3D Estimation, and embodied AI with Transformer based models.

• Open source project contributor.

• Comfortable working with SQL queries and ETL logic for data ingress.

• Experience with GCP or AWS, Kubernetes and Docker.