Senior Data Scientist, Fleet Performance Optimization

About Gridware

Gridware is a San Francisco-based technology company dedicated to protecting and enhancing the electrical grid. We pioneered a groundbreaking new class of grid management called active grid response (AGR), focused on monitoring the electrical, physical, and environmental aspects of the grid that affect reliability and safety. Gridware’s advanced Active Grid Response platform uses high-precision sensors to detect potential issues early, enabling proactive maintenance and fault mitigation. This comprehensive approach helps improve safety, reduce outages, and ensure the grid operates efficiently. The company is backed by climate-tech and Silicon Valley investors. For more information, please visit
www.Gridware.io
.

Role Description

As a Senior Data Scientist, you will be embedded within Gridware’s Fleet team, driving fleet performance optimization across our network of IoT devices.
You will work across hardware, firmware, connectivity, and backend systems to understand real-world system behavior and optimize performance end-to-end. A core focus of this role is balancing competing system constraints—such as
power consumption, data fidelity, connectivity reliability, and anomaly detection latency
—to ensure optimal fleet performance.
This role combines modeling, experimentation, and hands-on investigation to ensure reliable, scalable system performance in dynamic, real-world environments.

Responsibilities

- Develop models and analyses to optimize
system performance across competing constraints
(e.g., power usage vs data quality vs responsiveness)
- Define and implement
end-to-end observability
, establishing metrics across system components and dependencies
- Design and run experiments (e.g., pre/post, control vs test) to evaluate changes and detect regressions at both component and system levels
- Build and refine
anomaly detection and failure analysis
methods across complex, real-world data
- Lead
ad hoc investigations
into system issues, identifying root causes and driving resolution with cross-functional teams
- Translate insights into actionable recommendations across
Firmware, Hardware, Software, and Operations
, driving measurable improvements in system behavior
- Develop predictive systems for
early issue detection and performance forecasting
, including in environments with limited historical data
- Continuously evolve analyses into
scalable intelligence systems
that support monitoring, decision-making, and automation

Required Skills

- 5+ years of experience in data science working on
production systems or real-world applications
- Proven experience
building, deploying, and maintaining models in production environments
- Strong proficiency in
Python and SQL
- Experience working with
complex, real-world datasets
(e.g., time-series, event-based, or system-generated data)
- Strong foundation in
statistical analysis, experimentation, and/or anomaly detection
- Proven ability to
bring structure to ambiguous, open-ended problems
, iterating quickly to drive toward practical, high-impact solutions (80/20 mindset)
- Experience working cross-functionally with engineering and operational teams

Bonus Skills

- Experience working on
distributed hardware/software systems
such as robotics, autonomous vehicles, IoT fleets, charging infrastructure, or energy/grid systems
- Prior ownership of
end-to-end performance, reliability, or optimization
for large-scale, real-world systems operating in dynamic environments

This describes the ideal candidate; many of us have picked up this expertise along the way. Even if you meet only part of this list, we encourage you to apply!

Benefits

Health, Dental & Vision (Gold and Platinum with some providers plans fully covered)

Paid parental leave

Alternating day off (every other Monday)

“Off the Grid”, a two week per year paid break for all employees.

Commuter allowance

Company-paid training