Staff / Sr Software Engineer - Perception ML Systems

Aurora Innovation (View all Jobs)

Mountain View, California

Please mention No Whiteboard if you apply!
I'm a one-man team looking to improve tech interviews, and could use any support! 😄


Interview Process

1. Simplified real-world coding task on Coderpad.io 2. Time-boxed take-home assignment 3. Face-to-face meeting with teammates.

Programming Languages Mentioned

C++, Python


Who We Are

Aurora (Nasdaq: AUR) is delivering the benefits of self-driving technology safely, quickly, and broadly. Founded in 2017 by experts in the self-driving industry, Aurora is revolutionizing transportation – making it safer, increasingly accessible, and more reliable and efficient than ever before. Its flagship product, the Aurora Driver, is a platform that brings together software, hardware, and data services, to autonomously operate passenger vehicles, light commercial vehicles, and heavy-duty trucks. Aurora is partnered with industry leaders across the transportation ecosystem including Toyota, Volvo, PACCAR, Uber, Uber Freight, FedEx, and U.S. Xpress. Aurora tests its vehicles in the Bay Area, Pittsburgh, and Texas and has offices in those areas as well as in Bozeman, MT; Seattle, WA; Louisville, CO; and Detroit, MI. To learn more, visit www.aurora.tech.

Aurora hires talented people with diverse backgrounds who are ready to help build a transportation ecosystem that will make our roads safer, get crucial goods where they need to go, and make mobility more efficient and accessible for all. We’re searching for a Software Engineer to join Aurora’s Perception Evaluation team to accelerate model development and improve autonomy capabilities via advanced systems and algorithmic development

The ideal candidate will enjoy working across our autonomy codebase to accelerate ML model experimentation and data analysis to develop large-scale systems that produce interactive metrics and insights. You’ll architect large-scale data analysis systems and services, add new capabilities and feature improvements, and apply novel evaluation methodologies and algorithms that power our fleet of self-driving vehicles. The impact of your work will be fast, reliable, and safe ML models and will involve tight collaboration within Perception and across many models and teams, including Planning, Simulation, Cloud, Tools, and more. Responsibilities include:

In this role, you will

  • Accelerate model development and improve autonomy capabilities with advanced systems and novel algorithms
  • Build interactive ML evaluation systems that analyze and track autonomy performance 
  • Improve the on-device and offline performance of ML models through data insights, visualizations, training optimizations, and other advanced deep learning approaches
  • Improve the performance of the Perception module foveating attention on actors of importance to autonomous behavior through data insights, ML/deep learning approaches and visualizations
  • Build a large corpus of diverse events using data mining techniques that serves as the benchmark dataset for validating Perception performance
  • Significant ownership, independence, and leadership working across models and systems 

Required Qualifications

  • BS / MS / PhD degree in Computer Science or a related field
  • Excellent programming and software design skills in C++ or Python 
  • Expertise in Machine Learning, Computer Vision, and/or Autonomous systems
  • Experience with Machine Learning model evaluation methodologies and metrics
  • Comfort working on large codebases and software systems
  • Great collaboration and communication skills 

Desirable Qualifications 

  • Experience programming in a deep learning framework (e.g., PyTorch, Tensorflow)
  • Experience building distributed systems, web services, cloud computing systems, storage systems, or automated data pipelines
  • Experience with large-scale data analysis tools (e.g., Spark)
  • Familiarity with rich sensor data (e.g., LIDAR, RADAR, camera)
  • Familiarity with visualization libraries for 3D geometries and interactive visualization (eg.,three.js, matplotlib, bokeh)
  • Knowledge of model compression and performance optimization techniques, especially CUDA and GPU-accelerated software

 #LI-MD1

#Mid-Senior

Working at Aurora

At Aurora, we bring together people with extraordinary talent and experience united by the strength of our values. We operate with integrity, set outrageous goals, and continue to build a culture where we win together—all without any jerks.

We have offices in 8+ locations across the United States. We offer a competitive benefits package to qualifying employees. Our Career Page includes everything you need to know about working at Aurora.

At the core of everything we do is our commitment to safety. Building best-in-class self-driving technology will take time, and we believe that each employee at Aurora has a role in contributing to safety, every step of the way. Aurora expects commitment to our safety policies from every employee, and seeks candidates who take an active responsibility, can contribute to building an atmosphere of trust, and invest in the organization’s long-term success by prioritizing working safely, no matter what.

We believe that self-driving technology has broad benefits – including an increase in safety and access to transportation – and to achieve those benefits, we want and need a workforce with diverse experiences, insights, and perspectives; said another way, a workforce that reflects the communities and people our technology will benefit. You can find all the latest news on our Blog

Individuals seeking employment at Aurora are considered without regard to race, color, religion, national origin, age, sex, gender, gender identity, gender expression, sexual orientation, marital status, pregnancy status, parent or caregiver status, ancestry, political affiliation, veteran and/or military status, physical or mental disability, or any other status protected by federal or state law. 

Please mention No Whiteboard if you apply!
I'm a one-man team looking to improve tech interviews, and could use any support! 😄


Get weekly alerts of new jobs from companies not using whiteboard interviews!