Senior Applied Scientist - SLAM and Perception, Amazon Robotics

About the role

The Amazon Robotics Autonomous Mobility software team develops the autonomy software that powers Proteus, Amazon’s first fully autonomous warehouse robot. We are looking for a Senior Applied Scientist to join our perception and localization team. You will be part of an exceptional group of engineers building the platform and architecture for our onboard mapping, perception, motion planning and control software. In addition, you will collaborate with engineers and scientists across the team to develop and enhance our real-time multi-robot simulation capabilities.

Responsibilities

• Researching, designing, and implementing scientific approaches for sensor calibration, including cameras and LIDARs.
• Researching, designing, and implementing scientific approaches for SLAM (simultaneous localization and mapping).
• Sustaining and improving the large-scale deployment of a SLAM system shared across an autonomous robot fleet.
• Evaluating and integrating new sensing modalities into an existing autonomy software stack.
• Optimizing runtime performance of autonomy algorithms by exploiting underlying hardware acceleration capabilities.
• Building frameworks for large-scale replay and analysis of events in pre-recorded sensor data.
• Delivering high quality production level code (C++ or Python) and support systems in production.
• Collaborating with other functional teams in a robotics organization.
• Collaborating with hardware engineering team members on developing systems from prototyping to production level.
• Working with stakeholders across hardware and operations teams to iterate on system design and implementation.

Qualifications

• 3+ years of building machine learning models for business application experience
• PhD, or Master's degree and 6+ years of applied research experience
• Experience programming in Java, C++, Python or related language
• Experience with neural deep learning methods and machine learning
• Proven experience in robotic perception, SLAM, or computer vision
• M.S. or PhD in Engineering, Sciences, Mathematics or similar fields
• Excellent C++ or python programming skills including debugging, performance analysis, and test design

Preferred Qualifications

• Experience with modeling tools such as R, scikit-learn, Spark MLLib, MxNet, Tensorflow, numpy, scipy etc.
• Experience with large scale distributed systems such as Hadoop, Spark etc.
• PhD and 7+ years of relevant industry or academic research experience in developing algorithms for robotic perception.
• Expertise in C++, Python or any object oriented programming language
• Expertise in SLAM, 3D reconstruction, sensor calibration, or related fields
• Experience using sensors such as cameras, LIDAR, radar, sonar, GPS, IMU, etc.
• Track record delivering complex algorithms on robotic devices
• GPU programming experience (CUDA/OpenCL)
• Publishations in robotics and computer vision conferences and journals.

Benefits

• Medical, Dental, and Vision Coverage
• Maternity and Parental Leave Options
• Paid Time Off (PTO)
• 401(k) Plan

Pay

Base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location.

• USA, CO, Denver - 167,100.00 - 226,100.00 USD annually
• USA, MA, North Reading - 167,100.00 - 226,100.00 USD annually