Principal Data Scientist

Overview:
Passionate about 3D deep learning research and solutions that will impact the work of hundreds of thousands of users? Join our AI Prototypes Team and push the frontiers of artificial intelligence working with point clouds, photogrammetric meshes, oriented imagery, and elevation rasters to create new and exciting tools for 3D feature extraction and generation. This is a great opportunity to join a research-oriented team that works with the SOTA deep learning architectures and ideas, publishes its research results, and contributes to development of next-gen Esri software.

**Responsibilities**:

- Lead the team of data scientists and product engineers on R&D of Urban Scene Generator (USG) using deep learning architectures: LOD1 and textured LOD2+ buildings, street furniture, terrain, orthophoto, vegetation, and more
- Work with client-app teams’ stakeholders, like ArcGIS Urban and ArcGIS CityEngine, on understanding and accommodation of existing and emerging use-cases and integration paths of the USG service for improving productivity or adding new generative functionality deemed useful by the stakeholders
- Drive and contribute to neural network design and architectural decisions on generative neural networks, guide and do actual implementation, run distributed training, automated hyperparameter search
- Architect and work on implementation of the productization pipeline, including:

- Scalable and robust Inference-as-a-Service ArcGIS Online offering (USG service)
- MLOps and automated training, testing (sanity, functional, PDS), deployment
- Federation & Billing
- Guiding creation of training and inference datasets for generative models
- Establishing a framework for dataset versioning and tracking
- Defining USG lifecycle: versioning, synchronization of release cycle with client teams, models and API backward compatibility, reviewing documentation, working on “Explainability tools” for the Esri Tech Support team
- Stay current on latest SOTA developments in generative neural networks across multiple domains: raster, meshes, point clouds, LLM, and more
- Collaborate with other researchers and developers within and across the teams throughout the R&D process
- Be ready to advise on design and architectural decisions outside of the USG project
- Solve and articulate complex problems with design, development, and user experiences
- Additional R&D duties as assigned

**Requirements**:

- 8+ years of experience in the following fields: Machine Learning, Digital Signal Processing, Image processing, Linux
- Proficient in PyTorch, PyTorch Lightning, Distributed Data Parallel, Distributed Model Parallel
- Understanding of math behind and practical experience with GANs in general, Pix2PixHD-alike architectures in particular
- Knowledge of 2.5D & 3D formats and structures: OBJ format, Elevation rasters, Graph Neural Networks, Pytorch3d
- Solid experience with Ubuntu, Docker, Kubernetes, cloud computing, micro-services, ML serving
- Experience with ArcGIS Server REST API, Geoprocessing services, ArcGIS Pro
- Strong research background
- Excellent written and verbal communication skills
- Bachelor’s degree in computer or data science, mathematics, robotics, remote sensing, computer vision, or related field

Recommended Qualifications:

- Experience with C++, CGAL
- Familiarity with Differentiable Rendering
- Experience working with ArcGIS Urban, Esri CityEngine: working with multi-band rasters, CGA, Python and Geoprocessing automation, procedural content generation
- Knowledge of MLOps automation, Load (PDS) testing
- Familiarity with scalable CPU- or GPU-based processing of large volumes of GIS data, including GPU-based eigen-value, eigen-feature calculation for point clouds and elevation rasters
- Experience with NVIDIA RAPIDS, NVIDIA Kaolin, PyTorch Geometric
- Master’s degree or Ph.D. in computer or data science, mathematics, robotics, remote sensing, computer vision, or related field

The Company:
Our passion for improving quality of life through geography is at the heart of everything we do. Esri’s geographic information system (GIS) technology inspires and enables governments, universities, and businesses worldwide to save money, lives, and our environment through a deeper understanding of the changing world around them.

Esri is an equal opportunity employer (EOE) and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability status, protected veteran status, or any other characteristic protected by law.

LI-RC2