Research Scientist II

Research Scientist II

Amazon
3-6 years
Not Specified

Job Description


Job Description :
Road-network, Geospatial inputs and Routing inputs play a crucial role in Amazon Logistics last-mile vehicle routing problems. We own exciting science problems in the areas of Maps learning, Address Normalization, Geocode learning, Time estimations including route-time, delivery-time, transit-time predictions which are key to efficient planning and safe navigation. As part of the Last Mile Science & Technology organization, you'll partner closely with other scientists and engineers in a collegial environment to develop enterprise ML solutions with a clear path to business impact. We use a variety of Machine Learning, Deep learning, Computer vision and NLP techniques in our solutions. We are actively looking to hire scientists at various level to innovate and lead on these problem areas. Successful candidates will have a broad knowledge of Machine learning and Deep learning methods, the ability to graduate models to production, the communication skills necessary to explain complex technical approaches to a variety of stakeholders and customers, and the ability to take iterative approaches to tackle big, long term problems.
Some interesting problems we're solving today:
1. How can we solve a Travelling Salesman Problem which is typically solved using optimization techniques at scale using ML or Reinforcement learning with millisecond latency (We extended this challenge to MIT students, see here: https://lnkd.in/gqG_QVx )
2. How do you precisely locate the delivery location for a customer based on customer given address and historical data How will you solve this problem for new customers without any historical data
3. How can we estimate the travel time between point A to point B in road network using aerial imagery and latent space embeddings as features
4. Given a particular route spanning multiple buildings and commercial complexes, can we estimate the time it takes to deliver shipments in them accurately
5. How will you leverage Satellite/Aerial Imagery and augment with internal datasets to make the make map complete and correct
6. How do you build real-time CV systems that use street-view cameras to update the map at scale
Basic Qualifications :
. B.Tech or Masters in Computer Science, Mathematics, Statistics, or other quantitative field with exposure to statistical modeling and machine learning
. Applied work experience in machine learning for solving real-world problems in industry
. Proficiency in C/C++, Java, or Python
. Proficiency with at least one machine learning or statistical modeling library (R, Matlab, Scikit-learn)
. Past delivery of large-scale ML solutions for complex business problems
. Outstanding written and verbal communication skills
. Journal/Conference publications
Preferred Qualifications :
. PHD in Computer Science, Mathematics, Statistics, or other quantitative field with exposure to statistical modeling and machine learning
. Publications in top ML conferences or journals
. Experience with a popular deep learning toolkit (TensorFlow, MXNet, PyTorch, Caffe etc)

About Amazon

Amazon.com, Inc. is an American multinational technology company which focuses on e-commerce, cloud computing, digital streaming, and artificial intelligence. It is one of the Big Five companies in the U.S. information technology industry, along with Google, Apple, Microsoft, and Facebook.

Job Source : www.amazon.jobs

Similar Jobs

People Also Considered

Career Advice to Find Better

Simple body text this will replace with orginal content