Job Description
1. Utilizing statistical and mathematical tools including Data Visualization, Relational Databases, and Data Modeling & Evaluation to assess the quality, completeness, and relevance of input data.
2. Performing Exploratory Data Analysis to understand data distribution, stratify/normalize datasets, and prepare inputs for modeling.
3. Leveraging mathematical and statistical techniques to aggregate, and structure large datasets, data test hypotheses, perform statistical analysis, and identify candidate features for model development.
4. Working with Data Engineering teams to address missing data, handle outliers, and finalize variables used for modeling.
5. Designing, implementing, and maintaining Continuous Integration/Continuous Deployment (CI/CD) pipelines using GitHub Actions, Terraform, and Amazon Web Services (AWS).
6. Designing and building AI/ML infrastructure in Amazon Web Services (AWS) to support model deployment pipeline, data router, postprocessor in AWS, and model inference.
7. Designing, building, and experimenting with Machine Learning Models and Algorithms, comparing architecture and performance metrics to identify the optimal solution.
8. Configuring Deep Learning Neural Architectures and Long Short-term Memory (LSTM) networks to alert anomalous behaviors in unlabeled Internet of Things (IoT) data and detect anomalous behaviors in heterogeneous time-series data streams.
9. Identifying business insights using the selected Machine Learning Models and Deep Learning Networks including Data Extract, Transform & Load to generate business-consumable reports to support decision making.
10. Tuning model hyperparameters and architecture based on dataset characteristics and feedback loops to maximize predictive performance and construct variational autoencoder (VAE) to detect anomalous behaviors.
11. Formalizing and implementing production deployment plans for Machine Learning models, enabling real-time and batch scoring of future data to predict user behavior and support business operations.
12. Developing data visualization tools and dashboards to track model performance and support business reviews of key performance indicators (KPIs).
May telecommute.
This position requires two (2) years experience in the job offered or related occupation. Experience must include:
a. Developing feature engineering pipeline with rolling window approaches to enable utilization of non-time-aware algorithms for time-series data analysis.
b. Constructing variational autoencoder (VAE) to detect anomalous behaviors.
c. Implementing model deployment pipeline, data router, and postprocessor in AWS, using GitHub Actions, S3, Lambda, Batch, Step Function, and Sagemaker.
d. Exploratory Data Analysis, Machine Learning Algorithms, Deep Learning Networks and Data Modeling & Evaluation.
e. Data Extract, Transform & Load, Data Visualization, Relational Database, CI/CD Pipeline.
f. Configuring Long Short-term Memory (LSTM) networks to alert anomalous behaviors in unlabeled Internet of Things (IoT) data.
g. Leveraging mathematical and statistical techniques to aggregate and structure data, test hypotheses, perform statistical analysis, and build algorithmic solutions.
h. Designing and building AI/ML infrastructure in Amazon Web Services (AWS).
Masters (or foreign educ. equiv.) Degree in Statistics, Data Analytics, Machine Learning, or a related field.
$206,000 per annum. 40 hours per week; M-F.
Please copy and paste your resume in the email body (do not send attachments, we cannot open them) and email it to candidates at (link removed) with reference in the subject line.
Thank you.