Data Engineer - Digital Operations – Advanced Analytics

Talascend is currently seeking a Data Engineer - Digital Operations – Advanced Analytics for a contract opportunity in Warren, MI (Hybrid); Ability to work W2 Assignment

JOB TITLE: Data Engineer - Digital Operations – Advanced Analytics
DURATION: One year with possible extension
LOCATION: Warren, MI (Hybrid); Ability to work W2 Assignment

OVERVIEW:

This assignment will be working on technical cases. Providing data for all escalated customer complaints and cases from the connected vehicle. On Star, my brand apps, anything the vehicle connects with and uses. Any issues that the first line cannot resolve this team takes that on. This role will include a lot of problem solving and Data.  Connected Operations is a part of the larger Customer Experience organization and is at the forefront of the transition to a digital eco system where our interactions with our customers, our partners (dealers), now have more digital footprints. There are some major digital initiatives in the areas of NLP engines including speech to Text for IVR (Interactive Voice Response systems), transition to utilizing Intelligent Bots handling customer queries, using machine learning tools to improve our systems.  We are also responsible to ensure the transactional performance of in-vehicle product services (OnStar services delivered using cellular connection CDMA/LTE such as OnStar Vehicle Diagnostics, Vehicle Health Alerts, Theft Alert Notification, Hands Free Calling, Smart Driver, Turn-by-turn navigation instructions, automatic crash response roadside assistance and Family Link) and analysis of real time data collected from the vehicles in rapport with research and development , quality control and manufacturing to ensure customer safety and ownership experience. The Individual would be leading the effort to develop “first in line” insights, Key Performance Indicators (KPIs) and effectiveness of the solutions that are being implemented. The individual is responsible for providing technical expertise to develop analytics driven solutions to help achieve our business goal.  Individual will work as a member of a multi-disciplinary and cross organizational team of various experience levels that will be driving solution by designing, developing, and deploying analytic models to measure performance to support critical business areas.

PRIMARY RESPONSIBILITIES: 

As a Data Engineer, the individual will work with a wide variety of data sources including Oracle, Teradata, Greenplum, Hadoop databases to extract information and integrate to help create “key performance indicators” - The KPI’s would serve as a benchmark of the critical program’s success . The KPI’s would cover the aspects of operational health, effectiveness, and pain points of the digital implementation. Effective gap analysis to understand the failure rates and the cause of the failures is also a key responsibility. The individual would also be responsible for implementation of Text Analytics /ML programs to better our understanding of business analytics, train models to act as better predictors of the conversational intents (Text parsing and topic modelling), volumetric trends towards specific lines of business and overall pain point understanding. With multiple initiatives going on, there would be holistic integration in the strategy employed to achieve a unified picture of all programs. Gather the data through mining computer data through software, to improve performance and reduce costs. Effectiveness of the solutions through a cost model would also be a critical responsibility that the individual would work with along with a broader team.

• Identify the right data across multiple data platforms and analyze the data in those respective data platforms.
• Integrate utilizing ETL techniques (Extract, Transform and Load) , all the different data points to common data lake to support the creation of Key performance indicators.
• Ability to drive insights out of structured, unstructured and semi structured data.
• Lead for advanced text analytics.
  • Identify text splits/ Implement models like Bag of Words.
  • Ability to create topic categories from text analytics.
  • Help identify point pain points.
  • Ability to handle large data volumes.
• Lead for analytics on Big Data Volumes.
  • Ability to create systems from heavy duty vehicle data volumetric.
  • Integration across multiple systems, Databases, technology types.
• Self-starter and ability to form initial impressions from ambiguous data.
• Synthesize trend data to support recommendations for action to improve performance.
• Work in a agile environment with a fast paced team to quickly Key Performance Indicators.
• Recommend and apply the right machine learning algorithms to satisfy the appropriate business requirements.
• Create tools or systems using databases, Shell scripting, Cognos, Tableau, Power BI, Spreadsheet, Hadoop, Hue, Kafka, Grafana, Python for output.
• Maintain and update the tools, dashboards, databases, and Recommend Improvements.
• Identify and monitor current performance and potential service failure modes in delivering digital products to customers using analytics.
• Maintain knowledge management article with model documents, templates, detailed process flow diagram, value stream mapping diagram, swim lane diagrams, playbook, and other reusable knowledge assets.
• Generate standard reports summarizing operational costs by working with a broader team.
• Meet and gather requirements with multiple business stakeholders across projects in the digital ecosystem.
• Perform Proof of concept on newer tools and technologies (within the approved list of software) to drive innovation.
• Draft and document the business cases where machine learning models would be used – The benefits and the rationale for selecting a model approach.
• Identify the right dependent and independent variables to train the machine learning model sets; Run sample model sets to derive outputs that establishes the relationships between the variables clearly.
• Communicate with leadership to determine the service level agreement for performance of information technology and our back office.
• Identify and lead adaption of new and innovative technological advances taking place rapidly in the field to remain competitive.
• Troubleshoot production issues caused due to production incidents by providing tactical and innovative solutions by working closely IT teams in resolving identified systemic issues affecting system performance.
• Monitor and supervise timely release of software updates, Product tuning cycles, infrastructure upgrades, to ensure deadlines, standards and performance targets are met.
• Big data performance tuning for data ingestion and data retrieval, with modeling tools like Erwin, Visio and advanced level expertise in performance optimization, data transformation methods with languages/tools like SQL, PL/SQL, NoSQL, Hive, Hadoop, Spark.
• Gap analysis in compliance with operational excellence program (lean six sigma principals) of the system to provide insights and improving system performance.
• Understand architectural tenets of Clouds ecosystems.
• Understand ETL methodologies across multiple product ecosystems.

POSITION REQUIREMENTS: 

• Bachelor’s degree in Computer Science or related field required.
• Expert in utilizing SQL across Oracle, Hadoop/Hive databases, systems.
• Expert in ETL systems – Via Batch SQL, Data Stage (awareness).
• Experience with extraction and loading into Hadoop/Hive.
• Business Intelligence and Data Analysis Software — IBM Cognos Impromptu; Tableau, Oracle Business Intelligence Enterprise Edition.
• Operating System Software — Bash, UNIX, Shell Script.
• Knowledge of IVR (Interactive Voice Response Systems).
• Knowledge and Expertise in Vehicle-based Telematics Architecture.
• Specialized knowledge of Vehicle based Health programs, High Speed Telematics ingestion and backend -Vehicle communication.
• Database Management System Software — Apache Hadoop/HDFS; Oracle PL/SQL; Teradata Database, Apache Cassandra, Apache Hive, NoSQL database.
• Advanced proficiency with using text Analytics utilizing Hive.
• Familiarly and experience with implementing Machine Learning Models (Create data sets, train models, explain correlations between dependent and independent variables).
• Familiarity with Statistics and ability to explain why a specific model was chosen.
• Familiarity with Object or Component-Oriented Development Software — Python.
• Presentation Software — Microsoft PowerPoint.
• Project Management Software —Microsoft Project; Microsoft SharePoint.
• Development Environment Software —Eclipse IDE; Microsoft Visual Studio.

DESIRED QUALIFICATIONS:

• Knowledge of Data Lakes, Datawarehouse, Operational data stores as it relates to RDBMS and Big Data Technologies.
• Knowledge of Kafka Streaming Systems, Microservices architecture.
• Call-Center Telephony hardware/software integration to deliver critical Voice-based services.
• Knowledges of best CX practices for operational performance efficiencies – Determine right KPI’s, perform FMEA analysis, determine pain points, provide solutions for corrective actions.
• Understand Natural Language Processing.

#link