Job description
An extraordinarily talented group of individuals work together every day to drive TNS' success, from both professional and personal perspectives. Come join the excellence!
Overview
Have you ever received a phone call or text message from a scammer or other unwanted robocaller that you didn’t want? Has someone called you to get you to give out personal or financial information under suspicious circumstances? Would you like to know that when you get a phone call that it’s from a trusted source and they are who they say they are?Responsibilities
TNS Call Guardian solutions serve over a hundred million wireless and wireline subscribers across the US every day and provides industry-leading, real-time spam and fraud detection as well as reputation monitoring and management for thousands of enterprise customers. Our solutions combine data from multiple network solutions, proprietary and carrier-branded applications and feedback websites to score nearly 2 billion phone numbers in the US.
If you have a passion for building data processing and machine learning pipelines that impact huge numbers of everyday lives and have experience with large scale cloud-based data then the TNS Data Science team has an amazing opportunity for you in one of our US locations (Reston, VA or Seattle, WA).
The Data Engineer will work directly as part of our data science team, and partner with our software and service engineering team s to combine dozens of data sources , build data cleansing, processing, and feature pipelines to more accurately develop reputation scores for more than billions of telephone numbers and intercept attacks in real-time for tens of billions of phone calls every month.
Role s and Responsibilities
Construct data lake for machine learning pipelines from a variety of raw data sources that prepare and encode signals for use in classification and reputation scoring and spam/fraud detection algorithms .
Work with data scientists to analyze NLP data from customer feedback sources to cleanse, classify, and develop model features for classification and scoring algorithms .
Develop data pipelines and datasets that enable analysis of trends , root causes, and communicate relevant insights to assist product decision-making and identify emerging threats and spam campaigns .
Partner with engineer ing to understand existing product instrumentation, bridge gaps in data streams to assist data science programs, and design pipelines that can scale to handle billions of calls and be updated in near real-time.
Drive A/B/n tests and design of feature-level experiments to validate hypotheses and drive product development and algorithm ship decisions .
Automate data and ML pipelines using Tableau , Spark / Hive / SQL and AWS tools like Glu and SageMaker .
Analyze patterns to better understand network signals, call originator and subscriber behavior to drive further algorithm improvements and reduce noise-to-signal ratio .
Qualifications
- Prefer Master's degree in Data Science, Computer Science, Informatics, life sciences, physics, applied mathematics, statistics or related field . Equivalent , or equivalent additional e xperience and demonstrated product impact is acceptable in lieu of advanced degree(s) .
- 3+ years as a data engineer with familiarity with ML Ops and modern machine learning best practices.
- 3+ years working with diverse types of networking, telecom, or other real-world enterprise data sets – structured, semi-structured and unstructured data .
- 3+ years’ experience building production-ready ML systems, from preprocessing and normalization to monitoring model drift in a production environment .
- Advanced proficiency with SQL, Spark, Python, Scala, or Java for data pipeline, machine learning and AI applications for offline and online scenarios.
- Solid understanding of core statistical and modeling concepts, with experience using R, SAS, and especially Python for statistical analysis in applications for sampling, hypothesis testing (experimentation), prediction and/or classification.
- Strong understanding of Software Engineering and Development Life Cycle principles and best practices in machine learning development and deployment processes ( MLOps ).
- Experience with supervised and unsupervised Machine Learning techniques, with experience in time series/signal detection and NLP feature engineering and modeling highly preferred.
- Proficiency in leveraging cloud-based machine learning resources such as those from Amazon Web Services or Google Cloud for model training and productization .
- Collaborating via version control ( Git )
- Ability to thrive in a fast-paced multi-disciplinary environment; with the ability to effectively communicate with a diverse audience
- Experience with hyperparameter optimization, model selection and validation.
- Experience with implementation of solutions with DevOps tools in AWS or in cloud-hosted APIs .
- B eing familiar with agile methodology and issue / project tracking tools like JIRA or Azure DevOps.
If you are passionate about technology, love personal growth and opportunity, come see what TNS is all about!
TNS is an equal opportunity employer. TNS evaluates qualified applicants without regard to race, color, religion, gender, national origin, age, sexual orientation, gender identity or expression, protected veteran status, disability/handicap status or any other legally protected characteristic.
