Machine Learning Engineer

About the role

As a Performance Assurance Machine Learning Engineer, you will work under the coaching of Senior and Lead engineers of the Data Science & Tools Team to analyze Samsung’s deployed network elements. You will utilize skills to query databases to extract data, use Python or R to analyze data, identify 4G/5G network infrastructure and performance issues, and build prediction models, ad-hoc tools, and dashboards to communicate findings with your team and peers.

TeleWorld Solutions is a strategic wireless engineering and consulting firm offering network operators, OEMs, and tower companies turnkey design, optimization, network dimensioning, and deployment services. With experience from hundreds of thousands of successful implementations—including macro, DAS, Small Cells, and Wi-Fi—the world’s leading network operators and OEMs trust our knowledge and experience to plan, perform, troubleshoot, and implement technologies and solutions.

Responsibilities

• Work closely with internal and external stakeholders to explore relationships of 4G/5G KPI measurements and targets (KPI, KQI) for 4G/5G RAN product acceptance and performance monitoring.
• Collaborate with RF engineers, network engineers, data scientists, platform engineers, product teams, and operations stakeholders to ensure ML outputs are technically accurate, interpretable, and operationally useful.
• Utilize A/B testing, statistical, and machine learning models to build robust mechanisms for product and feature performance analysis, evaluation of new product and software releases, and third-party product evaluation.
• Aid in product and feature performance analysis, evaluation of new product and software releases, and third-party product evaluation using analytics and data science to drive intelligent business decisions.
• Proactively define and interpret data, metrics, and KPIs; analyze results; and provide insights to determine operational impact, trends, and opportunities for all 4G/5G RAN products.
• Prototype use cases, implement automations, and develop tools to support and augment manual or repetitive efforts.
• Communicate key findings to stakeholders using visualizations or other suitable methods.
• Compile analysis output and findings into a succinct story for technical and non-technical audiences.
• Adapt to changes in a dynamic business environment and support management initiatives.

Requirements

• 7+ years of professional experience in Data Science, Data Analytics, and/or Data Engineering with the ability to work with large datasets using demonstrated statistical, predictive modeling, and machine learning methods.
• 3-5 years of demonstrated experience designing, deploying, and maintaining large-scale ML systems in a production environment.
• Graduate degree in Computer Science, Statistics, Data Science, or a related field preferred.
• Programming experience in Python and Spark (preferred) and/or other languages such as R, SQL, Hive, Spark, JavaScript, Visual Basic, C++, or shell scripting in a Linux or IDE environment (e.g., VSCode, Jupyter, RStudio).
• Cloud development experience with AWS, Azure, or Google Cloud, utilizing platforms such as Databricks or Snowflake.
• Machine learning expertise in GLM Regression (Linear, Logistic, Multinomial), Decision Trees (including Boosted Trees, Random Forest), kMeans/Hierarchical Clustering, Principal Component Analysis, t-SNE, Neural Networks (e.g., transformers, auto-encoders), Bayesian Regression, and Time Series Modeling.
• Experience working with high-volume (1TB+) and high-dimensionality (500+ variables per schema) data, especially within big data frameworks (e.g., Hadoop, Citus, MongoDB).
• Experience performing data wrangling, exploratory data analysis (EDA), correlation analysis, statistical methodologies (distributions, hypothesis testing, confidence intervals), significance testing, and A/B testing.
• Experience with MLOps concepts and environments such as MLflow (a plus).
• Basic Linux administration and software development experience in a Linux environment.
• Experience with hardware resource management and configuration (e.g., CUDA, Docker, Kubeflow, Kubernetes) is a plus.
• Strong command of current data analytics technology trends, including emerging paradigms and practices.
• Demonstrated research and problem-solving skills via prior work experience.
• Experience with wireless infrastructure providers and/or operators is desired.
• Technical knowledge of wireless technologies and procedures (e.g., CDMA, EVDO, LTE, VoLTE, 5G) is a plus.
• Experience evaluating service performance trends and proactively defining RAN system performance-related issues is a plus.
• Experience with software version control, coding best practices, and development management tools (e.g., GitHub, Bitbucket) is desired.
• Strong work ethic, integrity, and the ability to work independently or in a team environment.
• Excellent interpersonal and communication skills, with the ability to develop and maintain good working relationships at all levels within and outside the company.
• Curiosity and eagerness to learn, with the ability to quickly grasp statistical methods and methodologies.
• Ability to operate a computer keyboard and view a video display terminal for more than 75% of work time in an office environment.

Benefits

TeleWorld Solutions offers great benefits and is certified as "A Great Place to Work." We are a veteran-friendly team and invite veterans and veteran spouses to bring their skills and dedication to our workforce.