Simelabs - Data Science Engineer - Machine Learning

DATA SCIENCE ENGINEERAirline industry is going through a drastic transformation in the area of retailing and distribution that requires very advance data analytics support to optimize revenue performance and customer experience.Recently introduced concepts of Offer/Order Management and Continuous Dynamic Pricing significantly expand opportunities for engaging with travelers through multiple touch points and creating personalized offers accounting for individual preferences and market context.These practices can substantially benefit from a combination of statistical and machine learning techniques leveraging huge volumes and variety of consumer and competitive data available in airline industry.The Data Science Engineer applies expert level statistical analysis, data modeling, and predictive analysis on strategic and operational problems in airline industry.As a key member of the Sabre Operations Research team, you will leverage your statistical and business expertise to translate business questions into data analysis and models, define suitable KPIs, and graphically present results to a wide range of audiences including internal and external clients, sales, and development team.In addition, you will source data from multiple different data sources, write high-quality data manipulation scripts in R, Python, Perl, bash, etc, develop and apply data mining and machine learning algorithms for advanced analysis and prediction.You will also utilize your strong communication skills to work with developers to support product development cycles and decision makers who need empirical data to promote sales and growth.Responsibilities :- Work with subject matter experts from airlines to identify opportunities for leveraging data to deliver insights and actionable prediction of customer behavior and operations performance.- Assess the effectiveness and accuracy of new data sources, data gathering and forecasting techniques.- Develop custom data models and algorithms to apply to data sets and run proof of concept studies.- Leverage existing Statistical and Machine Learning tools to enhance in-house algorithms.- Collaborate with software engineers to implement and test production quality code for AI/ML models.- Develop processes and tools to monitor and analyze data accuracy and models performance.- Demonstrate software to customers and perform value proving benchmarks.- Calibrate software for customer needs and train customer for using and maintaining software.- Resolve customer complaints with software and respond to suggestions for enhancements.Required Qualifications :- Advanced Degree in Statistics, Operations Research, Computer Science, Mathematics, or Machine Learning.- Proven ability to apply modeling and analytical skills to real-world problems.- Knowledge of machine learning techniques (clustering, decision tree learning, artificial neural networks, etc.) and statistical concepts (regression, properties of distributions, statistical tests, etc.).- Solid programming skills 2- 3 languages out of R, SQL, Python, TensorFlow, PySpark, Java, JavaScript or C++.- Absolutely must have graduate school level knowledge of Revenue Management models and algorithms.- Experience (minimum 4 out of 7) with deployment of machine learning and statistical models on a cloud :1. MLOps within the enterprise CI/CD process for ML models 2. Experience deploying ML APIs in production environments in GCP using GKE 3. Experience in using GCP Vertex AI for ML and BigQuery 4. Knowledge in Terraform and Containers technologies 5. Experience writing data processing jobs using GCP Dataflow and Dataproc 6. Experience setting up ML model monitoring and autoscaling for ML prediction jobs7. Understanding of machine learning concepts to scale ML across different services by leveraging Feature Store, Artifacts Registry and Analytics Hub (ref:hirist.tech)