Staff Data Scientist

Calix

About The Position

Calix enables broadband service providers to simplify operations, grow revenue, and deliver exceptional subscriber experiences through Calix Cloud - a cloud-native platform powered by the Intelligence platform, which delivers AI-driven insights across broadband networks, services, and subscriber environments. Role Overview As a Staff Data Scientist focused on Calix Cloud and Intelligence, you will apply advanced analytics and machine learning to broadband access network, service, and subscriber telemetry data. You will work closely with senior data scientists, engineers, and product teams to build models and insights that power network intelligence, service assurance, and subscriber experience analytics within Calix’s cloud platforms. This role is ideal for PhD candidates with min 5 yrs of experience who want to translate research into production-grade AI capabilities embedded directly into Calix Cloud products.

Requirements

PhD in Data Science or Computer Science
Strong foundation in statistics, probability, and linear algebra
Experience working with large-scale time-series and telemetry datasets typical of broadband analytics
Hands-on experience with ML techniques, including: Regression and classification Clustering and dimensionality reduction Time-series analysis and forecasting Anomaly detection and change-point detection
Experience with model evaluation, validation methods, and performance metrics
Strong programming skills in Python and familiarity with ML libraries NumPy, pandas, SciPy, scikit-learn
Strong SQL skills for large-scale data analysis
Ability to write clean, maintainable, and testable code
Experience with data preprocessing, feature engineering, and exploratory data analysis (EDA)
Experience in analyzing broadband network and service telemetry
Ability to work with metrics such as latency, throughput, packet loss, utilization, and device-level signals
Understanding of noisy, incomplete, and delayed data common in broadband environments
Ability to reason about data across devices, subscribers, locations, and time windows
Strong problem-solving skills and the ability to translate ambiguous product or network problems into analytical solutions
Clear written and verbal communication skills
Experience presenting insights through charts, dashboards, and reports

Nice To Haves

Experience or research in broadband access networks, subscriber analytics, or network intelligence
Familiarity with Calix-relevant broadband technologies such as Fiber (PON), Cable (DOCSIS), and Wi-Fi telemetry
Experience with cloud-native data platforms (AWS, GCP, Azure) and ML deployment frameworks
Exposure to MLOps practices, including CI/CD, model monitoring, and lifecycle management
Knowledge of real-time analytics, streaming data, or large-scale data ecosystems
Publications or applied research in network analytics, anomaly detection, forecasting, or machine learning

Responsibilities

Analyze and model large-scale broadband telemetry and time-series data used by Calix cloud, including throughput, latency, packet loss, utilization, and device-level metrics, and many more.
Develop and validate ML models for Upsell, cross-sell, churn prevention, customer acquisition, anomaly detection, performance forecasting, fault classification, and capacity prediction that drive proactive network insights
Build features and models supporting network health scoring, service quality monitoring, and subscriber Quality of Experience (QoE) analytics
Apply advanced techniques such as time-series modeling, change-point detection, and probabilistic modeling to real-world broadband data
Collaborate with data engineering and platform teams to develop and integrate models into Calix Cloud’s cloud-native analytics pipelines
Perform EDA, feature engineering, and data preprocessing for scalable, production pipelines
Help scale analytics and ML solutions across millions of access devices, subscriber endpoints, and Wi-Fi environments
Design experiments and evaluate the business and operational impact of analytics on network performance and subscriber experience
Build scalable ML pipelines and deploy models into production environments.
Communicate insights clearly to product, engineering, and customer-facing teams via dashboards, reports, and presentations
Translate ambiguous product and operational problems into well-defined data science and ML solutions
Follow best practices in model lifecycle management, including versioning, validation, and deployment monitoring