Geospatial Data Science Engineer

Organization and Background

Established in 1996, Esri India Technologies Pvt. Ltd. (Esri India), the market leader in geographic information system (GIS) software, location intelligence, and mapping solutions in India, helps customers unlock the maximum potential of their data to improve operational and business decisions. It has delivered pioneering enterprise GIS technology, powered by ArcGIS, to more than 6,500 organizations in government, private sector, academia, and non-profit sectors. The company has also introduced ‘Indo ArcGIS’, a unique GIS solution & data offering suited for government organizations. Esri India collaborates with a rich ecosystem of partner organizations to deliver GIS and location intelligence-based solutions. Headquartered in Noida (Delhi NCR), the company has 1 million users in the country and has got Great Place to Work Certified® in 2021, 2022, and 2023.

Website : overview

5+ Years of experience is required in practical machine learning, Proven data science and AI skills with Python, PyTorch and Jupyter Notebooks, Deep Learning.

This position will work closely with customer to understand their needs to develop and deliver models for India specific GeoAI use cases. He / she will be responsible for conceptualizing and developing solutions using ESRI products. Additionally, the role demands representing the organization at conferences and forums, showcasing expertise and promoting ESRI solutions. Should be capable of working independently, exhibiting strong problem-solving skills, and effectively communicating complex geospatial concepts to diverse audiences.

Roles & Responsibilities

Consult closely with customers to understand their needs

Develop and pitch data science solutions by mapping business problems to machine learning or advanced analytics approaches

Build high-quality analytics systems that solve our customers’ business problems using techniques from data mining, statistics and machine learning

Write clean, collaborative and version-controlled code to process big data and streaming data from a variety of sources and types

Perform feature engineering, model selection and hyperparameter optimization to yield high predictive accuracy and deploy the model to production in a cloud, on-premises or hybrid environment.

Implement best practices and patterns for geospatial machine learning and develop reusable technical components for demonstrations and rapid prototyping

Integrate ArcGIS with popular deep learning libraries such as PyTorch

Keep up to date with the latest technology trends in machine and deep learning and incorporate them in project delivery

Support in estimation and feasibility for various RFPs

Desired skillset

5+ years of practical machine learning experience or applicable academic / lab work

Proven data science and AI skills with Python, PyTorch and Jupyter Notebooks

Experience in building and optimizing supervised and unsupervised machine learning models including deep learning and various other modern data science techniques

Expertise in one or more of the following areas :

Traditional and deep learning-based computer vision techniques with the ability to develop deep learning models for computer vision tasks (image classification, object detection, semantic and instance segmentation, GANs, super-resolution, image inpainting, and more)

Convolutional neural networks such as VGG, ResNet, Faster R-CNN, Mask R-CNN, and others

Transformer models applied to computer vision

Expertise in 3D deep learning with Point Clouds, meshes, or Voxels with the ability to develop 3D geospatial deep learning models, such as PointCNN, MeshCNN, and more

A fundamental understanding of mathematical and machine learning concepts such as calculus, back propagation, ReLU, Bayes’ theorem, Random Forests, time series analysis, etc

Experience with applied statistics concepts

Ability to perform data extraction, transformation, loading from multiple sources and sinks

Experience in data visualization in Jupyter Notebooks using matplotlib and other libraries

Experience with hyperparameter-tuning and training models to a high level of accuracy

Experience in LLMs is preferred.

Self-motivated, life-long learner

Non-negotiable skills

Master's degree in RS, GIS, Geoinformatics, or a related field with knowledge of RS & GIS

Knowledge and experience of ESRI products like ArcGIS Pro, ArcGIS Online, ArcGIS Enterprise, etc

Experience with Image analysis and Image processing techniques in SAR, Multispectral and Hyperspectral imagery.

Strong communication skills, including to non-technical audiences

Should have strong Python coding skills

Should be open to travel and ready to work at client side (India)