Machine Learning Engineer / Data Scientist - Climate and Energy Policy

Planet Reimagined•New York City, NY

18h•Remote

About The Position

Planet Reimagined is seeking a Machine Learning Engineer / Data Scientist to design and build cutting-edge data systems that accelerate climate solutions across local and federal scales. Join our mission-driven team building one of the world's first ML systems for hyper-local policy analysis and recommendations. You'll design, train, and deploy models, and build the knowledge graphs, wikis, and other structured datasets behind them, to identify successful climate interventions, predict how they adapt to new contexts, and optimize renewable energy deployment from city councils to federal land management. Founded by a multi-platinum musician and a UN advocate, Planet Reimagined was built on the belief that big change happens when people act together and when that action drives shifts in policy and industry. On a mission to deliver fair solutions for people and the planet, we use an innovative action research method to incubate and scale creative solutions to our most pressing climate problems. We mobilize fans at concerts to take real-time civic action, and we help renewable energy companies access public lands once closed to them. From legislative wins to global campaigns, we turn bold ideas into action. And we’re just getting started. Join a team of creative problem-solvers dedicated to advancing global climate solutions. The Machine Learning Engineer / Data Scientist will build the data infrastructure powering insights for climate policy, renewable energy optimization, and scalable climate interventions. This role will work at the intersection of data engineering, AI/ML, and climate policy, developing tools to help communities and governments replicate successful climate solutions.

Requirements

3-5 years of experience in data science and ML engineering, preferably in GCP/AWS/Azure ecosystem
Strong proficiency in LLM application design, context engineering strategies, Python, and SQL
Hands-on experience building functional knowledge systems for LLM applications
Proven ability to work with varied, unstructured data sources including municipal records and reports, news coverage, video documentation, and government datasets.
Strong problem-solving skills and ability to thrive in ambiguous climate policy and energy environments
Excellent communication skills for cross-functional collaboration with policy experts, community stakeholders, and federal planners including turning data analysis into data storytelling outputs.
Core Stack: Python, SQL, BigQuery, GCP/AWS/Azure services
Data Tools: Pandas, NumPy, dbt, Apache Beam/Dataflow
API Development: REST APIs, government data integrations, real-time community sentiment and federal climate data augmentation
Infrastructure: Cloud Functions, Pub/Sub, Cloud Run, CI/CD with Cloud Build
Databases: BigQuery (primary), Firestore, vector databases (Vertex AI Vector Search, Pinecone)
Ability to pass a background check.
Ability to provide 3 professional references including a recent supervisor

Nice To Haves

Background or strong interest in climate policy, municipal governance, federal land management, or energy transition planning
Experience with government data sources, regulatory documents, federal climate records, and civic data standards
Knowledge of policy analysis frameworks, community engagement measurement, and renewable energy development processes
Previous work in mission-driven organizations focused on local government, federal policy, or climate action

Responsibilities

Build LLM-powered knowledge graphs, wikis, and other structured datasets from policy documents, municipal records, community sentiment, and federal energy data, along with the human-readable layers rendered from them.
Develop LLM and NLP pipelines that extract policy elements, resolve entities, and link them across sources
Track data provenance so every policy element traces back to its source document, passage, and extraction method
Design human-in-the-loop workflows where policy experts validate extracted policy elements, and their corrections improve the models, scripts, and prompts
Construct policy timelines by extracting and ordering events to show how climate solutions unfold over time
Design, train, and deploy models for policy effectiveness scoring, solution replicability, and energy development potential
Build recommendation and graph-based models that match proven climate policies to a specific city, county, or community
Own the full modeling lifecycle: baselines, feature engineering, model selection, tuning, and error analysis
Develop evaluation frameworks to measure model, extraction, and LLM output quality against expert-validated ground truth
Analyse community-stentiment data to quantify support for climate policies within surveyed localities
Build systems to facilitate rigorous comparative analysis, helping policy experts map when, where, and how policies succeed and identify causal dynamics that may transfer to other contexts.
Analyze policy timelines to measure adoption lags, implementation speed, and time to impact
Perform exploratory analysis and predictive modeling to find patterns in climate solution adoption and renewable energy development opportunities
Communicate findings through visualizations and automated reporting for climate and energy transition planning
Deliver insights from the analysis of interaction and call-to-action conversion data to improve in-concert advocacy efforts
Build reproducible training, evaluation, and deployment pipelines with experiment tracking, versioning, and a model registry
Automate CI/CD for models, with validation gates and staged rollouts
Maintain the data pipelines and API integrations (BigQuery, Cloud Functions) that feed models from government, community, and federal data sources
Monitor model performance, data drift, and knowledge graph quality, with data governance for sensitive municipal data and PII.