• Support development of algorithms that detect and interpret changes in system behavior and predict the timing of future maintenance needs
• Apply statical-based and data-driven methods to optimize algorithm performance
• Develop tools to automate cleaning, manipulation, and analysis of large data sets using languages such as Python, SQL.
• Support development of state of the art analytics tools & methodologies to enable expansion of health monitoring capability across PWC business segments.
• Support root cause analysis of in-service issues and incorporate lessons learned into improved design standards
• Proficiency in manipulating and analyzing large, complex, multi-dimensional data sets
• Naturally inquisitive and skilled in exploratory data analysis, formulating and testing hypotheses
• Results-oriented and motivated to provide solutions with measurable benefit to our customer and business
• Use Data Analysis to Metrics to indicate the Quality Health of… an Engineering Development Project
• Use Data visualization to determine and present metrics in clear, concise dashboards for all levels of management to understand the meaning and make data-driven decisions
• Learn and understand data sources
• Create AI/ML prototypes for use cases requiring identifying entity/objects, determining object association, object disambiguation, anomaly detection, state estimations, etc.
• Develop and maintain data models (both physical and logical)
• Perform extraction, transform, and load (ETL) tasks related to the different modalities and algorithms being applied. This data ETL includes identifying the data’s relevant metadata to ensure consistency, quality, accuracy, integrity, and information assurance and security.
• Conduct anomaly detection using various AI/ML techniques
• Use algorithms to identify complex patterns across multiple modalities
• Increase the efficiency and quality of data alignment and fusion
• Enhance and maintain analysis tools, including automation of current processes using AI/ML algorithms
• Direct quantitative data analysis including developing retrieval, processing, fusion, analysis, and visualization of various datasets
• Configure and program prototypes Jupyter notebooks with ML solutions
• Setup and use AWS instances to train and operate AI/ML models
• Practical experience with statistical analysis
• Expert software development skills lifecycle including developing and maintaining good production quality code
• With at least 5 years of experience as a Data Scientist or any related role (non-negotiable)
• Experience with Deep Learning Frameworks such as Keras, Tensorflow, PyTorch, Mxnet, etc.
• Ability to apply these frameworks to real problems in the ‘time -series’ domain
• Ability to communicate with clarity and precision
• Hands-on Software Development Skills (Python-Preferred)
• Experience or educational courses/projects in Machine Learning, and/or Text
• Visualizations/Web Development Skills (e.g. Power BI, Tableau, D3, etc)
• Experience with the following will be highly desirable; Python, • Power BI Tableau, Jupyter Notebooks, Teradata, Hadoop/Hive, SQL
• Hands-on experience with prototype development
• Hands-on experience with automating data cleansing, formatting, staging, and transforming data human
• Hands-on experience applying data analytics
• Hands-on experience with intelligent systems and machine learning
• Experience with interpretability of deep learning models
• Big Data Skills (Azure, Hadoop, Spark, recent deep learning platforms)
• Experience with text mining tools and techniques including in areas of summarization, search (e.g. ELK Stack), entity extraction, training set generation (e.g. Snorkel), and anomaly detection
•Exposure to Alterix is added advantage.
Big Data Analytics, Computer Vision, Data Mining, Data Science, Data Standards, Data Strategy, Deep Learning, Machine Learning, Microsoft Azure, Microsoft Azure Databricks, Power Bi, Python, Statistical Learning, Tableau Desktop