Principal Applied Scientist, Last Mile Delivery Automation; Fulfillment & Operations

Principal Applied Scientist, Last Mile Delivery Automation

Job  |  Services LLC

As a Principal Applied Scientist for Last Hundred Yards Automation, you will be at the forefront of developing AI and ML solutions that power our autonomous delivery robots. This role combines deep expertise in machine learning, computer vision, and robotics to solve complex challenges in real‑world autonomous navigation, obstacle detection, and dynamic path planning. You will work closely with robotics engineers, software developers, and product teams to research, design, and implement sophisticated algorithms that enable safe and efficient last‑yard delivery operations.

The position requires a unique blend of theoretical knowledge and practical implementation skills, with a focus on transforming research concepts into production‑ready solutions that can operate reliably in diverse real‑world environments.

• Lead development and implementation of advanced AI/ML models for autonomous navigation, focusing on real‑time object detection, semantic scene understanding, and predictive movement planning.
• Design and conduct experiments, analyze complex datasets, and develop novel algorithms to improve robot performance and reliability.
• Collaborate with cross‑functional teams to integrate ML solutions into the robotics platform, optimize model performance for edge computing, and establish metrics for continuous improvement.
• Mentor junior scientists, contribute to research publications, and stay current with latest developments in the field.
• Develop robust ML pipelines, implement state‑of‑the‑art deep learning architectures, and create innovative solutions for challenges such as adverse weather navigation, multi‑robot coordination, and human‑robot interaction.

LMDA (Last Mile Delivery Automation) is an automation system designed to revolutionize the final phase of package delivery, focusing specifically on the last hundred yards from delivery vehicle to customer doorstep. The system integrates autonomous robots equipped with advanced AI/ML algorithms, real‑time navigation capabilities, and smart obstacle avoidance technology to efficiently transport packages to their final destination.

These robots navigate various terrains, including sidewalks, building entrances, and residential complexes, while adhering to local safety regulations and maintaining secure delivery protocols. LMDA incorporates cloud‑based fleet management, real‑time tracking, and dynamic route optimization to ensure seamless coordination between delivery vehicles and robots.

The system features a user‑friendly interface for both delivery personnel and customers, providing live tracking, delivery notifications, and interactive robot communication. As labor costs rise and delivery volumes increase, LMDA represents a scalable, cost‑effective solution that addresses the growing challenges of last‑mile delivery while significantly improving operational efficiency and customer satisfaction.

• 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.

• Experience with modeling tools such as R, scikit‑learn, Spark MLLib, MxNet, Tensor Flow, Num Py, Sci Py, etc.
• Experience with large‑scale distributed systems such as Hadoop, Spark, etc.

Base salary range:  –  USD annually (USA, WA, Bellevue). Final compensation includes sign‑on payments and restricted stock units, and is determined by experience, qualifications, and location. Comprehensive benefits include health, dental, vision, prescription, life insurances, EAP, mental health support, flexible spending accounts, adoption and surrogacy reimbursement, 401(k) matching, paid time off and parental leave. Learn more at (Use the "Apply for this Job" box below)..

Amazon is an equal‑opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.