Data Science Engineer (Infrastructure & Network Analytics)

Job description

Data Science Engineer (Infrastructure & Network Analytics)This role has been designed as ‘Hybrid’ with an expectation that you will work on average 2 days per week from an HPE office. **Who We Are:** Hewlett Packard Enterprise is the global edge-to-cloud company advancing the way people live and work. We help companies connect, protect, analyze, and act on their data and applications wherever they live, from edge to cloud, so they can turn insights into outcomes at the speed required to thrive in today’s complex world. Our culture thrives on finding new and better ways to accelerate what’s next. We know varied backgrounds are valued and succeed here. We have the flexibility to manage our work and personal needs. We make bold moves, together, and are a force for good. If you are looking to stretch and grow your career our culture will embrace you. Open up opportunities with HPE. **Job Description:** ***Job Family Definition:*** Designs, develops and applies programs, methodologies and systems based on advanced analytic models (e.g. advanced statistics, operations research, computer science, process) to transform structured and unstructured data into meaningful and actionable information insights that drive decision making. Uses visualization techniques to translate analytic insights into understandable business stories (eg. descriptive, inferential and predictive insights). Embeds analytics into client’s business processes and applications. Combines business acumen and scientific methods to solve business problems. ***Management Level Definition:*** Contributions impact technical components of HPE products, solutions, or services regularly and sustainable. Applies advanced subject matter knowledge to solve complex business issues and is regarded as a subject matter expert. Provides expertise and partnership to functional and technical project teams and may participate in cross-functional initiatives. Exercises significant independent judgment to determine best method for achieving objectives. May provide team leadership and mentoring to others. **Role Overview** We are seeking a highly skilled **Data Science Engineer** to drive the development of our next-generation Predictive Assurance and Real-Time Health Analytics platform. In this role, you will design, deploy, and optimize data pipelines, statistical algorithms and machine learning models that monitor, analyze, and forecast the health of our enterprise-grade routing fleet (including Juniper QFX Series nodes). You will bridge the gap between heavy-duty Data Engineering and Advanced Machine Learning, implementing stateful batch analytics engines to detect insidious regressions like memory leaks, alongside deep learning models to predict physical hardware failures in our optical layer. **What You'll Do:** - **Predictive Modeling:** Design and refine time-series forecasting models (e.g., BiLSTM, Transformers, or Prophet) to predict optical performance and failure markers. - **Feature Engineering:** Translate complex network telemetry (DOM metrics, FEC counters, BER, and thermal data) into actionable features for real-time anomaly detection. - **Distributed Computing & Data Pipelines:** 5+ years of production experience with **Apache Spark** (PySpark/Scala) utilizing advanced windowing, state manipulation, and memory-efficient aggregations. - **Machine Learning Frameworks:** Proven experience deploying **LightGBM** (or XGBoost) and Deep Learning frameworks (TensorFlow/Keras or PyTorch for **LSTMs/BiLSTMs**) into live production environments. - **Production Engineering:** Lead the transition of models from R&D/Lab environments into our production Datacenter Assurance platform, ensuring scalability, low-latency, and high availability. - **Diagnostic Analytics:** Develop statistical "Health Index" algorithms to identify currently degraded optics, moving beyond simple threshold alerts to intelligent, multivariate diagnostics. - **Collaboration:** Partner with network hardware engineers and software architects to understand failure signatures and integrate data-driven insights into our monitoring workflows. **What You Need to Bring:** - **Experience:** 5+ years of professional experience in a Data Science, Machine Learning, or AI Engineering role. - **Core Skills:** Expert-level proficiency in Python and deep learning frameworks (PyTorch or TensorFlow). - **Modeling:** Strong background in time-series forecasting, anomaly detection, and multivariate analysis. - **Engineering:** Production-level coding experience; familiarity with CI/CD, Docker, Kubernetes, and MLOps best practices. - **Data Handling:** Proficiency with SQL and large-scale data processing frameworks (e.g., Apache Spark, Kafka); bonus skills - Apache Flink, Apache Storm - **Domain Knowledge:** Familiarity with network telemetry, signal processing, or hardware performance metrics is a significant plus. **Preferred Skills:** - Experience with network monitoring systems or optical transceiver diagnostics. - Expertise in statistical profiling (e.g., Z-score, Change-Point Detection, Dynamic Time Warping). - Experience optimizing ML models for resource-constrained environments or high-throughput real-time systems. **Domain Knowledge:** - **Infrastructure/Network Telemetry Domain:** Experience working with time-series metrics generated by network devices, operating systems, or cloud infrastructure (e.g., RES/RSS memory components, process-level statistics, Junos/Linux kernel behavior). - **Optical Systems Familiarity:** Basic understanding of fiber-optic or telecom infrastructure, specifically **DOM (Digital Optical Monitoring)** properties. - **MLOps Mindset:** Experience with containerized deployment (Docker, Kubernetes) and model lifecycle tracking tools (MLflow, Kubeflow). **Education and Experience Required:** - PhD degree in Statistics, Operations Research, Computer Science or equivalent preferred and 3+ years of relevant experience. Or Master´s Degr