Note: The job is a remote job and is open to candidates in USA. Recurve is hiring a Senior Data Scientist to help build the next generation of the FLEX Platform, working with one of the largest energy datasets available. The role involves leading data science activities that combine statistical modeling, machine learning, and AI techniques to support the effective deployment of demand-side energy resources.
Responsibilities
- Working under limited supervision, lead the development and refinement of statistical and ML models for load, flexibility, and customer behavior
- Analyze AMI, customer, and grid data to identify patterns for system planning and program design models
- Apply sound judgment to select the appropriate statistical, machine learning, or deep learning approach for each problem
- Review methods and collaborate with other data scientists to improve analytical approaches
- Collaborate with domain experts to ensure models reflect real grid behavior, program design, and customer characteristics
- Validate models with structured backtesting, cross-validation, and uncertainty analysis
- Communicate assumptions, limitations, and tradeoffs clearly to cross-functional partners
- Develop efficient and maintainable code and models
- Produce clear, reproducible documentation
- Partner with customer-facing teams to support customer engagements and develop new analytical approaches that can be incorporated into the FLEX Platform
- Translate customer requirements and field experience into reusable platform capabilities
Skills
- Senior-level ability to lead analytic work with moderate to high complexity (equivalent to 5-8 years of relevant experience post Bachelor's degree; advanced degree preferred)
- Expertise in a variety of modern supervised and unsupervised machine learning techniques
- Experience applying data science to energy systems, demand response, energy efficiency, distributed energy resources, utility operations, or other complex physical systems
- Strong Python and SQL skills with experience developing clean, production-ready code
- Depth in Python data science tools like pandas, NumPy, SciPy, scikit-learn
- Experience with time-series and panel data analysis
- Strong data visualization skills
- Experience supporting customer-facing analytical projects or translating customer requirements into production software
- Solid grounding in statistics, uncertainty, and causal reasoning
- Ability to collaborate effectively with data science and engineering colleagues and influence cross-functional partners
- Ability to communicate technical concepts effectively with both technical and non-technical stakeholders
- Demonstrated ability to balance analytical rigor with practical engineering tradeoffs
- Hands-on neural-network modeling using frameworks like PyTorch or TensorFlow
- Experience with sequence modeling or deep learning for time series
- Experience with geospatial modeling and analysis
- Experience with DER device-level data
- Experience with agentic code development workflows
- Interest in ML approaches adaptable to distributed or device-adjacent inference
- Advanced degree in engineering, physics, mathematics, or related technical discipline
Company Overview