Senior Data Scientist

The Opportunity

Reporting to the Director of Software Engineering, you will work closely with Software Engineers, Product, Operations, and business stakeholders to own the full lifecycle of forecasting and optimization models: from data pipelines and feature engineering through model training, deployment, monitoring, and production support.

As a senior applied ML practitioner, you will be responsible for both the data systems and the machine learning workflows that produce reliable forecasts, insights, and operational decisions for our stakeholders.

This work matters. Even a small change to optimize power utilization can have a huge impact on our customers, our electrical grid and our environment. We’re building something that will have a lasting, positive impact.

We'repassionate about your growth, offering exciting opportunities for conferences, continuous learning, and professional development.

Work on a cutting-edge platform built from the ground up with no tech debt, leveraging modern technology, best practices, and clear documentation with detailed flowcharts.

Our new Senior Data Scientist / ML Engineer will:

Deliver. You have strong analytical and problem-solving skills to find solutions to complex problems and drive high-risk initiatives to completion on time, on budget.

• Implement and maintain data pipelines that are secure, reliable and scalable by design to support data science projects and real-time energy grid data pipelines

• Own the full lifecycle of time-series forecasting models, including data preparation, feature engineering, model training, validation, deployment, monitoring, retraining, and production support.

• Develop, train, tune, andoperateTemporal Fusion Transformer models and other time-series forecasting approaches for energy market, grid, asset, and customer use cases.

• Deploy machine learning models into production using practical MLOps patterns, including reproducible training workflows, model versioning, inference pipelines, monitoring, and rollback strategies.

• Build andmaintainAirflow DAGs that orchestrate data ingestion, model training, batch inference, validation, and downstream reporting workflows.

• Diagnose data quality, model performance, and pipeline reliability issues; implement durable fixes so problems only happen once.

• Diagnose and troubleshoot problems; implement changes so problems only happen once

• Support disaster recovery and operational readiness for critical data pipelines, model workflows, and production forecasting systems.

Report. You will monitor and report on progress, methodically evaluate processes and systems to improve efficiency; and implement processes that provide transparency and tracking.

• Monitor and report on data pipeline health, data quality, model performance, forecast accuracy, drift, and production incidents.

• Establish transparent tracking for model experiments, training runs, deployment status, and operational performance.

• Create dashboards, alerts, and documentation that make production data and ML systems understandable to engineering, product, and business stakeholders.

Collaborate. You have strong interpersonal and communication skills to keep everyone on the same page when working cross-functionally.

• Collaborate with software teams to understand and document the sources of data from production applications.

• Collaborate with stakeholders to integrate models, forecasts, and various types of data into production applications.

• Provide technical guidance and coaching to influence the design, development and testing of cloud applications that produce data,

Grow. With an obsessive passion for product development at the bleeding edge of innovation and curiosity for continuous development, you will bring your expertise to create scalable systems.

• Continuously improve the reliability, scalability, observability, and performance of data pipelines and production ML systems.

• Stay current with practical advances in time-series forecasting, MLOps, cloud data platforms, and energy analytics.

• Bring a pragmatic, production-focused mindset to model development: balancing accuracy, interpretability, maintainability, and operational value.

What you will bring to Peak Power:

The experienceand education.

• Bachelor’s degree in software engineering, computer science or related technical field (e.g. EE, physics or mathematics), or equivalent practical experience

• AWS certifications, or equivalent practical experience

• 5+ years of practical experience across data science, machine learning engineering, data engineering, or similar technical roles, with strong Python skills and experience taking models from development into production.

• Experience deploying and maintaining containerized cloud applications (e.g. Docker) and cloud functions (e.g. AWS Lambda)

• Experience working with relational and time series databases, like Postgres,TimescaleDB,ClickHouseandInfluxDB

• Experience with data workflow orchestration tools such as Apache Airflow or Luigi

• Experience with MLOps platforms such as Kubeflow, AWS SageMaker, or Google Vertex AI

• Experience with infrastructure-as-code software such as Terraform or Pulumi

• Experience with large-scale data processing and distributed computing frameworks such as Apache Spark and Apache Flink is a nice to have.

• Experience building a data lake using Amazon S3, or similar technologies

• General knowledge of software development, APIs, data stores, networking, security, machine learning and cloud computing services

The drive and curiosity.

• You are self-sufficient in troubleshooting and resourceful in uncovering mysteries

• Continuously learning new frameworks and technologies to generate innovative solutions</