Staff Software Engineer, Perception

Aurora•Mountain View, CA

29d•$171,000 - $303,000•Hybrid

About The Position

Aurora’s mission is to deliver the benefits of self-driving technology safely, quickly, and broadly. The Aurora Driver will create a new era in mobility and logistics, one that will bring a safer, more efficient, and more accessible future to everyone. At Aurora, you will tackle massively complex problems alongside other passionate, intelligent individuals, growing as an expert while expanding your knowledge. We’re searching for a Staff Software Engineer and Machine Learning practitioner to join the Perception Tracker Team at Aurora. In this role, you will play a critical part in elevating the Aurora Driver’s perception performance and expanding our driverless operational domain across key routes throughout the United States. Your work will be fundamental to scaling our mission, directly contributing to the delivery of self-driving benefits safely, quickly, and broadly.

Requirements

Master's degree or higher in Computer Science, Robotics, Electrical Engineering, or a related field (or Bachelor with 2+ years of relevant industry experience in software engineering).
Proficient software engineering skills in C++ and Python, with a focus on writing clean, scalable, and efficient production-quality code.
Working knowledge in one or more focus areas of ML: deep learning, computer vision, recursive state estimation, structured prediction, optimization, and others.
Experience with PyTorch, Tensorflow, and/or other deep learning frameworks

Nice To Haves

Experience deploying production-grade CV/ML models within real-time computing environments.
Strong grasp of fundamentals: linear algebra, discrete and continuous optimization, supervised and unsupervised methods, generative and discriminative methods, and Hidden Markov Models.
Hands-on experience with VLM, foundational or world models.
Hands-on experience in CUDA or high-performance GPU programming for accelerated computing.
Publication record at top-tier robotics/computer vision conferences/journals, or strong industry experience in relevant fields (robotics, computer vision, self-driving technology)
Demonstrated experience automating ML workflows and optimizing training pipelines for efficiency.
Contributions to open source project(s)
Proven ability to thrive in highly collaborative, cross-functional engineering environments.

Responsibilities

Tackle end-to-end perception challenges, including tracking dynamic actors, recognizing actions and attributes, and developing deep semantic understanding of diverse traffic environments.
Research and develop state-of-the-art deep learning and machine learning models to enhance perception performance in challenging, real-world scenarios, such as highway and urban driving, long-range multi-sensor tracking, and degraded sensor conditions.
Collaborate cross-functionally to iterate on the Perception system, translating insights from on-road and simulated testing into robust, high-quality, and well-tested software solutions.
Drive the software development lifecycle from prototype to production, focusing on large-scale data analysis and the deployment of performing, production-ready solutions on the real-time Aurora Driver platform.
Contribute to architectural strategy and team collaboration, ensuring our perception systems remain scalable, efficient, and at the forefront of autonomous driving technology.
Design and implementation of state-of-the-art object tracking algorithms.
Design algorithms to extract, leverage, and fuse complementary information from different sensors.
Design and implement state-of-the-art ML systems for object tracking and attribute estimation leveraging expertise in recursive state estimation, Hidden Markov models, structured prediction, and sequential models.
Build and improve model pipelines for large-scale and efficient model training.
Analysis of failure modes and implementation/testing of solutions to address the surfaced issues