Principal Engineers, Software

T-Mobile T-Mobile · Telecom · Bellevue, WA +1

Principal Engineers, Software at T-Mobile will detect and resolve problems by analyzing large amounts of data, defining new metrics and business cases, designing simulations and experiments, creating machine learning (ML) software and models, and collaborating with experts to develop closed-loop analytics and automation software solutions and reporting. They will collaborate with software developers and system engineers to design, implement, and deploy software for ML solutions, perform datamining and modeling to discover insights, operationalize models, and identify opportunities through the use of machine learning, algorithmic, and visualization techniques. They will analyze large scale telemetry data and build models that predict failure of T-Mobile network assets, radios, FRU and basebands, and leverage business objectives, systems, and data pipelines to operationalize ML in large-scale environments. The role involves improving neural network model efficiency via parameter and structure tuning and developing software in support of multiple machine learning workflows and integrating and deploying code in large-scale production environments.

What you'd actually do

  1. Collaborate with software developers and system engineers to design, implement, and deploy software for ML solutions which meet customer requirements, scale easily, and support deployment in highly available environments.
  2. Perform datamining and modeling to discover insights, operationalizing models and identifying opportunities through the use of machine learning, algorithmic, and visualization techniques.
  3. Analyze large scale telemetry data and build models that predict failure of T-Mobile network assets, radios, FRU and basebands.
  4. Ability to think outside the box to develop new algorithms and methods for novel solutions to challenging business problems.
  5. Perform research and work with technical teams to implement new and emerging technologies that will facilitate better data integrity, reliability, and enrichment for quantitative solutions.

Skills

Required

  • machine learning algorithms, including Deep Learning, Multilayer Perceptron, Recurrent Neural Networks, Convolutional Networks, Auto Encoders, Variational Auto Encoders, Bayes Point Machine, Deep Semantic Networks, Fast Fourier Transform, Latent Dirichlet Allocation, Random Forest, Randomized PCA, Anomaly Detection, and Gradient Boosted Trees
  • Deploying at least one of the following models for machine failure prediction: Classification or Anomaly Detection
  • Scala programming with Spark experience
  • F# programming language
  • machine learning model in construction and inference with ML.Net
  • model structure and parameter tuning using Grid search and evolutionary optimization methods

What the JD emphasized

  • machine learning (ML) software and models
  • operationalizing models
  • predict failure
  • implement new and emerging technologies
  • operationalize ML
  • improve neural network model efficiency
  • integrate and deploy code in large-scale production environments

Other signals

  • ML software and models
  • operationalizing models
  • predict failure
  • implement new and emerging technologies
  • operationalize ML
  • improve neural network model efficiency
  • integrate and deploy code in large-scale production environments