Position: Environmental Data Engineer / Machine Learning Engineer
Position Type: Full-Time
Reports to: Jay Weeks, Director of Data & Soil Science

REQUIRED QUALIFICATIONS

• Bachelor’s or Master’s degree in Computer Science, Data Science, Machine Learning, Environmental Science, or a related field.
• 3+ years of experience in data engineering, with a proven track record of productionizing prototype code in a startup or fast-paced environment.
• Strong proficiency in programming languages such as Python (with libraries like Pandas, NumPy, Scikit-learn) and SQL.
• Experience with ML frameworks (e.g., TensorFlow, PyTorch, XGBoost) and timeseries analysis (e.g., Prophet, LSTM networks, PINNs).
• Hands-on experience with cloud platforms, containerization, and CI/CD pipelines.
• Familiarity with geospatial data processing and environmental modeling concepts, particularly in soil science or agriculture.
• Excellent problem-solving skills, with the ability to handle ambiguous requirements and deliver under tight deadlines.

PREFERRED SKILLS

• Experience in digital soil mapping, carbon stock prediction models, advanced statistics, and/or Bayesian model calibration / inference
• Knowledge of big data technologies (e.g., Spark, Kafka) for handling large-scale timeseries datasets.
• Background in DevOps practices and infrastructure as code (e.g., Terraform).
• Passion for sustainability and environmental impact.

ROLE OVERVIEW

As a Data Engineer / Machine Learning Engineer, you will play a pivotal role in bridging the gap between experimental prototypes and scalable, production-ready systems. You’ll spend approximately 50% of your time optimizing and deploying data pipelines to support long-term business needs, and the other 50% developing advanced machine learning models for environmental mapping and predicting changes in environmental metrics (e.g., soil organic carbon stocks) using time series data. This is a hands-on position in a fast-paced startup environment, where you’ll collaborate with cross-functional teams to deliver impactful, reliable solutions.

KEY RESPONSIBILITIES

• Production Pipeline Development (50% of time):
• 
  
  
  
• Evaluate and refactor prototype code from R&D phases into efficient, maintainable production pipelines.

• Design, implement, and maintain scalable data ingestion, processing, and ETL (Extract, Transform, Load) workflows using cloud-based infrastructure (e.g., AWS, GCP, or Azure).
• Ensure pipelines are robust, fault-tolerant, and optimized for performance, security, and cost-efficiency.
• Integrate monitoring, logging, and alerting systems to support ongoing operations and quick issue resolution.
• Collaborate with software engineers, scientists, data scientists, and other stakeholders to align pipelines with business objectives, enabling long-term scalability and reliability.
• Model Development (50% of time):
• 
  
  
  
• Build, train, and deploy machine learning models for environmental quantification (e.g., digital soil mapping, predicting soil organic carbon stock changes, etc.).

• Work with time series data from various sources (e.g., satellite imagery, sensor data, historical records) to develop predictive models using techniques like time-series forecasting, geospatial analysis, and deep learning.
• Perform feature engineering, model evaluation, hyperparameter tuning, and validation to ensure accuracy and generalizability.
• Integrate ML models into production environments, including API development for real-time predictions and batch processing.
• Stay abreast of advancements in ML for geospatial and environmental applications, experimenting with new algorithms and tools to improve model performance.
• General Duties:
• 
  
  
  
• Conduct code reviews, write documentation, and mentor junior team members on best practices in data engineering and ML.

• Troubleshoot and debug issues in both data pipelines and ML systems.