"Postdoctoral Associate – Machine Learning"

The Urban Systems Lab (USL) at New York University seeks a Postdoctoral Associate in Machine Learning to support the development, optimization, and deployment of machine learning models for ClimateIQ, an AI-enabled climate risk assessment tool. ClimateIQ supports urban decision-makers and frontline communities by generating localized insights for climate hazards such as flooding and extreme heat.

This position will focus on advancing machine learning workflows, geospatial data processing, and cloud-based model deployment. The Postdoctoral Associate will work closely with climate scientists, urban researchers, and software engineers to ensure robust model performance, scalable data pipelines, and reproducible research outputs. The role is well suited to candidates interested in applied machine learning research with direct policy and societal relevance.

Responsibilities

• Assist with the technical development of the Machine Learning models for ClimateIQ and integration with Google Cloud Platform.
• Troubleshoot and refine Machine Learning models to ensure model performance and accuracy.
• Ensure seamless data integration into ML data pipelines, working closely with ML researchers.
• Optimize cloud and HPC-based processing pipelines for large-scale data handling
• Enable seamless integration and deployment of ML models on Google Cloud Platform.
• Collaborate with interdisciplinary team members to align technical solutions with project goals.

In compliance with NYC’s Pay Transparency Act, the annual base salary range for this position is $75,000. New York University considers factors such as (but not limited to) the specific grant funding and the terms of the research grant when extending an offer.

Required Qualifications

• Applicants must hold a PhD degree in a relevant field such as Data Science, Computer Science, Statistics, or a related discipline, with all degree requirements completed by the time of hire.
• Extensive experience in Machine Learning, including applications of ConvLSTM and CNN.
• Proficiency in working with geospatial data.
• Strong understanding of machine learning data pipelines and preprocessing techniques.
• Experience with cloud-based platforms (e.g., Google Cloud Platform) for scalable machine learning and data processing.
• Advanced proficiency in Python, including libraries such as NumPy, Pandas, and Xarray, as well as deep learning frameworks like TensorFlow/Keras.
• Excellent communication and organizational skills, with the ability to effectively convey complex technical concepts to both technical and non-technical audiences.

Preferred Qualifications

• PhD degree
• Familiarity with climate and urban datasets.
• Familiarity with C++ and Fortran.
• Familiarity with R and relevant data science libraries, with experience in cloud-based environments and scalable data processing for model deployment.

Please include current CV, cover letter and proof of degree.