Software Development Engineer- Machine Learning
- New York, NY
The Items and Offers platform (IOP) manages the global catalog at at the heart of the systems that support the world's largest e-Commerce platform. We serve as the gateway for the millions of merchants that offer the earth's largest selection of products to Amazon customers, at a rate of hundreds of billions of updates on billions of catalog items every single day.
The relationships between catalog items are a first class architectural concern at Amazon, which the Items and Offers Platform Relationships team in NYC have ownership of.
The Catalog Relationship team is working to innovate in the space of inferring, managing, and presenting relationships between items in the catalog to drive better product discovery and customer experience while navigating Amazon's large and ever-growing catalog. Work in this space ranges from building high performance large scale distributed real-time systems, data modeling to capture new relationship structures, machine-learning based inference systems, and experiment frameworks that enable continuous measurement, feedback and improvement.
As a Software Development Engineer- Machine Learning of this team, you will
• Build and own systems, services and tools for inference, automation and maintenance of catalog relationships.
• Translate high-level, ambiguous business goals into technical specifications and break down the technical specifications into concrete tasks.
• Partner with Applied Scientists and Machine Learning community to built highly scalable machine learning solutions for inferring and maintaining catalog relationships.
• Automate the ML model development life-cycle and accelerate the development, testing and deployment of ML models to production.
• Write a high quality distributed system software that harnesses the power of Machine Learning to make inference decisions.
• Be a technical partner for the leadership and guide their business and technical decisions.
• AWS (i.e. SageMaker, Glue, SQS, Kinesis, EMR, Lambda etc.)
• Spark/Hadoop (big data)
• RDS and DynamoDB
• Machine Learning(SparkML, TensorFlow, Keras, Deep Learning)
• Jupyter and Zeppelin (ML notebooks)
• Java, Scala, Python, React.JS
• Distributed Real-Time Streaming Systems
• Elastic Computing
• Massively Distributed Systems
Every day we are working hard, having fun and making history - and we would love you to work with us. If you have what we are looking for, come join a strong team in a highly visible organization. Your impact on our software will be felt around the world.
• Have experience in building highly concurrent distributed systems for online services at scale
• 6+ years of work experience in software development
• Have project Lead experience
• Have knowledge of Object-Oriented Design, data structures, algorithm design, and complexity analysis
• Have strong proficiency in, at least, one modern programming language such as C, C++, C#, Java, Python, Scala or Perl
• Bachelor's Degree or higher in Computer Science or related field
• Experience mentoring junior engineers
• Experience building complex software systems that have been successfully delivered to customers
• Experience developing service oriented architectures and an understanding of design for scalability, performance and reliability.
• Experience working in ML and Big Data technologies.
• Experience defining system architectures and exploring technical feasibility tradeoffs.
• Knowledge of professional software engineering practices & best practices for the full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations
• Ability to take a project from scoping requirements through actual launch of the project
• Experience in communicating with users, other technical teams, and management to collect requirements, describe software product features, and technical designs.
• Have a strong sense of ownership, urgency and drive
• Be a strong leader with a desire to mentor and lead people
• BA/BS in computer science or equivalent experience
• 3+ years of work experience or relevant experience with a PhD in CS or related field
• 2+ years of work experience building large-scale production ML systems
• Experience with ML libraries/frameworks such as Keras, Tensorflow, AWS Sagemaker
• Experience of Software development in one or more of the general purpose programming languages: C/C++, Go, Python, Java
• Desire and ability to write production quality code
Amazon is an Equal Opportunity Employer.
Back to top