Company Description

Pitch Aeronautics (www.pitchaero.com) is a rapidly growing startup creating game-changing solutions for the utility industry. We’ve developed a drone to install our innovative line sensor, bird diverters, and other equipment directly onto power lines. Our drone-deployable line sensors wirelessly transmit real-time environmental and line data to a secure online platform—helping utilities push more power through existing lines, reduce wildfire risk, and improve grid reliability.

We’re seeking a talented Machine Learning Engineer to help us harness weather and environmental data to build better forecasting models and drive smarter grid operations. This role focuses specifically on developing and deploying ML models that analyze weather patterns, forecast conditions along transmission lines, and support real-time decision-making for utility operators.

At Pitch, we’ve fostered a collaborative, fun, “get-stuff-done” work environment. We move fast, prototype quickly, and empower team members from day one. If you want to shape next-generation climate-aware energy infrastructure, we’d love to meet you.

Learn more about our company at:

-Our website: https://www.pitchaero.com/

-Our Linked-In posts: https://www.linkedin.com/company/11764600/

-Our Facebook posts: https://www.facebook.com/pitchaero

-Here's a video of our drone performing a sensor installation on an energized power line: https://youtu.be/S9F0jz4eqNY?feature=shared

Role Description

This is a part-time, on-site role based in Boise, Idaho. As an ML Engineer focused on weather data and forecasting, you will design and deploy machine learning models that improve our ability to predict wind, temperature, solar radiation, and other environmental factors along high-voltage transmission corridors. Your models will power our analytics platform, enabling more accurate Dynamic Line Ratings (DLR) and helping utility companies mitigate wildfire and outage risks.

You’ll work across weather datasets, time-series sensor data, and geospatial models to extract insights that improve operational planning and real-time decision-making.

Responsibilities

• Develop machine learning models that forecast weather and environmental conditions (wind speed, ambient temperature, solar radiation, etc.) at high spatial and temporal resolution
• Integrate real-time weather data, forecast models, and sensor data into predictive pipelines that support grid planning and risk analysis
• Apply time-series analysis, ensemble learning, and probabilistic modeling techniques to generate high-confidence forecasts
• Work closely with hardware and software teams to ensure models are effectively integrated into our analytics platform
• Build scalable data pipelines for ingesting, cleaning, and processing weather and IoT sensor data
• Quantify uncertainty in model outputs and develop confidence intervals for DLR recommendations
• Collaborate with product managers and utility partners to refine use cases and tailor models to real-world needs
• Optimize and deploy ML models using AWS tools and cloud infrastructure (e.g., SageMaker, Lambda, EC2)
• Document model methodologies, assumptions, and performance for internal and customer use

Minimum Qualifications

• Bachelor’s or Master’s degree in Computer Science, Atmospheric Science, Data Science, Machine Learning, or a related field
• Strong experience in machine learning using Python (e.g., Scikit-learn, XGBoost, TensorFlow, or PyTorch)
• Familiarity with weather forecasting models, meteorological datasets, or climate modeling frameworks
• Experience working with time-series data, regression models, and forecasting techniques
• Ability to build data pipelines for large datasets, especially geospatial or sensor-based data
• Strong analytical and problem-solving skills, with attention to uncertainty quantification and model validation
• Experience with AWS tools (SageMaker, EC2, Lambda, S3, etc.) for model development and deployment
• Must be a U.S. citizen or lawful permanent resident (due to ITAR/government contract requirements)

Desired Qualifications

• Experience with physics-informed machine learning, Gaussian Processes, or Bayesian modeling
• Prior work with NOAA datasets, wind/solar irradiance models, or numerical weather prediction (NWP) systems
• Background in energy systems, utilities, or climate risk modeling
• Currently located in Boise or the Treasure Valley area
• Experience building models for operational decision-making in real-time environments