nybl builds machine learning solutions for artificial lift optimization in upstream oil and gas. The stack—C#, .NET, Python, MATLAB, SQL, plus SCADA integration—reflects domain-specific engineering: real-world control systems tied to data pipelines. Active projects cluster around ESP (electric submersible pump) failure prediction and artificial lift efficiency, with pain points centered on downtime reduction and performance digitization, suggesting the platform moves from reactive maintenance into predictive operations.
nybl is a machine learning platform serving oil and gas operators seeking to optimize artificial lift systems, particularly electric submersible pumps (ESPs). The product ingests production and sensor data, applies predictive models to forecast failures and identify efficiency gains, and surfaces actionable recommendations to field teams. The company operates from Dubai with a small, senior-heavy engineering team and sales presence across the Middle East and North America, positioning for regional deployments in high-production regions.
nybl's core stack includes C#, .NET, Python, MATLAB, and SQL, with SCADA integration for real-time control systems. This combination supports both data modeling (MATLAB, Python) and production deployment (.NET, C#).
nybl has 8 active roles focused on engineering (5), sales (2), and product (1). Active hiring spans the United Arab Emirates, Saudi Arabia, Qatar, and the United States, with most roles at senior level.
nybl's active projects include ESP failure prediction models, artificial lift optimization solutions, and the lift.ai advanced analytics platform. Work centers on digitizing artificial lift systems and reducing downtime through predictive intelligence.
Other companies in the same industry, closest in size