We are looking for an Applied Scientist to push the boundaries of machine learning and simulation at scale. As a member of PXT Finance, you will own the development of distributed simulations for population dynamics forecasting and expense planning. This will include the development of state-of-the-art time series and survival models leveraging deep learning techniques such as Graph Neural Networks, Recurrent Neural Networks, and Transformers. Working on a cross functional team, you will collaborate closely with data scientists, software engineers, product managers and finance managers. This is a high-impact role where you will develop applications that will be used by planners and decision makers across Amazon.

Key job responsibilities
- Lead the development of distributed simulations for population dynamics forecasting and expense planning.
- Implement state-of-the-art graph deep learning models for tasks such as node survival analysis and spatio-temporal time series forecasting.
- Collaborate with cross-functional teams, including data scientists, software engineers, and product managers, to integrate forecasting solutions into Amazon’s cost planning processes.
- Leverage big data processing frameworks such as Apache Spark to ingest high volume headcount data into machine learning workflows.
- Apply GPU programming frameworks such as PyTorch and CUDA to deploy fast and scalable planning solutions.
- Push the boundary of machine learning-based simulation and publish results in peer-reviewed journals.


A day in the life
As an Applied Scientist in Finance you will focus on data science and machine learning engineering workflows. This means ownership of models from the idea stage all the way to production deployment. In addition to programming and system design you'll also work with customers, partners, and leaders to guide project decisions

About the team
We are a small team of scientists with a focus on forecasting and simulation applications for expense and headcount planning. By keeping pace with the advance of machine learning technology are rapidly scaling our productivity and impact. We strive to deliver efficient and innovative solutions by constantly developing and improving our research and engineering skills.

BASIC QUALIFICATIONS

- 3+ years of building models for business application experience
- PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
- Experience programming in Java, C++, Python or related language
- Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing

PREFERRED QUALIFICATIONS

- Experience in professional software development
- Experience using big data frameworks such as Spark and Hadoop

Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.

Our compensation reflects the cost of labor across several US geographic markets. The base pay for this position ranges from $136,000/year in our lowest geographic market up to $222,200/year in our highest geographic market. Pay is based on a number of factors including market location and may vary depending on job-related knowledge, skills, and experience. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, please visit https://www.aboutamazon.com/workplace/employee-benefits. This position will remain posted until filled. Applicants should apply via our internal or external career site.