Data Scientist

Description

Life at Plume

At Plume, we believe that technology isn't about moving faster, it's about making life’s moments better. Which is why we’ve built the world's first, and only, open and hardware-independent service delivery platform for smart homes, small businesses, enterprises, and beyond. Our SaaS platform uses WiFi, advanced AI, and machine learning to create the future of connected spaces—and human experiences—at massive scale.

We now deliver services to over 60 million locations globally and have managed over 3 billion devices on our platform. We’re expanding rapidly, pioneering a new category, and we achieved our Series F funding in just four years. Our customers include many of the world's largest Internet Service Providers (ISPs) who look to Plume to help them evolve their smart home offerings while gleaning insights from their own data.

With a bias for action and a love for being trailblazers, the team at Plume embodies a combination of relentless curiosity and imaginative innovation. We challenge ourselves to think in ways that other companies don't, work to do what should be done (rather than what can), and if we can’t do it exceptionally well, we don’t do it. It’s how we've assembled a team of world-class builders, thinkers, and doers. And it’s how we’re reinventing what’s possible every day.

Role Description:

We’re looking for a hands-on, impact-oriented Data Scientist who thrives on solving complex problems with data. You’ll design, build, and deploy data-driven models that extract insight from network traffic and telemetry data — while shaping the features, datasets, and pipelines that power those models. You’ll also play a key role in understanding business and technical requirements, translating them into concrete data analyses, experiments, and production-ready solutions — often working under tight delivery timelines.

Responsibilities

• Manipulate, clean, and transform large-scale datasets of network and device telemetry for modeling and analysis.
• Design and implement feature engineering strategies that enhance model accuracy, interpretability, and robustness.
• Use SQL and Python (Pandas, NumPy, Scikit-learn, etc.) to explore data, build analytical pipelines, and deliver reproducible results.
• Translate product or business needs into well-scoped analytical tasks and model development plans.
• Build and evaluate machine learning models for anomaly detection, forecasting, and optimization.
• Collaborate closely with engineering and product teams to integrate models into production systems and monitor their performance.
• Balance experimentation with execution — delivering insights and models efficiently under tight schedules.
• Contribute to MLOps workflows for model deployment, validation, and monitoring.

Requirements

• Strong programming skills in Python and experience with core data science libraries
• Solid SQL skills for querying, aggregating, and joining complex datasets.
• Proven experience transforming messy, high-volume data into structured, high-quality inputs for modeling.
• Deep understanding of feature extraction, selection, and transformation for predictive modeling.
• Strong grasp of statistics, probability, and applied machine learning.
• Ability to understand requirements, scope solutions, and deliver high-quality results on tight timelines.
• Excellent communication and teamwork skills across engineering, product, and data functions.
• About Plume
• As the creator of the only open, hardware-independent, cloud-controlled experience platform for ISPs and their subscribers, Plume partners with over 400 ISP customers, including some of the world’s largest such as Charter, Liberty Global, and J:COM.
• Using OpenSync, the most widely supported open-source, silicon-to-cloud framework for smart spaces, Plume’s software-defined network allows ISPs to decouple their service offerings from hardware and rapidly curate and deliver new services over a multi-vendor, open-platform architecture.