Data Scientist II

AWS Infrastructure Services owns the design, planning, delivery, and operation of all AWS global infrastructure. We support data centers, servers, storage, networking, power, and cooling equipment to ensure continuous customer access to cloud services. We work on challenging problems involving complex supply chain variables and seek talented individuals to join us.

You will join a diverse team of engineers, supply chain specialists, security experts, and operations managers. Collaborating across AWS, you'll help uphold safety and security standards while providing extensive capacity at low cost, fostering an inclusive culture that encourages bold ideas and ownership.

We are looking for a highly motivated Data Scientist to develop scalable, predictive, and prescriptive analytics solutions supporting AWS Supply Chain and Procurement. You will work with stakeholders, data engineers, BI engineers, and analysts to achieve strategic goals.

The ideal candidate has a strong background in optimization, machine learning, and statistical modeling, with excellent communication skills to translate data insights into actionable recommendations. You should be comfortable working independently in a fast-paced, ambiguous environment.

Key Responsibilities

1. Perform feature engineering on large datasets, conduct exploratory data analysis, and build models using time series forecasting techniques such as ARIMA, ARIMAX, Holt Winter, and ensemble methods.
2. Apply supervised learning algorithms (linear/logistic regression) and unsupervised algorithms (k-means, PCA, market basket analysis).
3. Solve optimization problems related to inventory and network optimization, with hands-on experience in linear programming.
4. Collaborate with business, engineering, and partner teams to align focus areas and deliver insights.
5. Address unstructured problems with a detail-oriented approach, owning tasks from start to finish.
6. Develop data sets and models to answer key business questions, working closely with stakeholders.
7. Leverage distributed machine learning and statistical algorithms to process large data volumes for customer service.

Qualifications

• Masters with 5+ years or Bachelors with 8+ years in a quantitative field (e.g., CS, Math, ML, Stats, Operations Research).
• Proficiency in Python, R, or similar scripting languages; experience with SQL, MySQL, and databases.
• Expertise in machine learning, statistics, and optimization, including linear programming.
• Experience with statistical measures such as hypothesis testing, confidence intervals, and error analysis.
• Excellent communication skills for technical and non-technical audiences.

Preferred additional skills include experience with Perl or other scripting languages, large tech company roles, and AWS services like S3, Glue, Athena, Sagemaker, Lambda, EC2, Batch, and Step Functions. Ability to create compelling data visualizations is also valued.

We encourage candidates from diverse backgrounds to apply, even if they do not meet all preferred qualifications. AWS promotes an inclusive culture with opportunities for mentorship and career growth. For accommodations during the application process, please visit