Data Scientist - Traffic Simulation and Street Optimization
Role details
Job location
Tech stack
Job description
-
Drive the design, implementation and deployment of traffic simulation and street optimization products and services.
-
Lead a focused group of software development and product engineers.
-
Design efficient architectures and develop on top of existing traffic simulation solutions: macro, meso, micro scales:
-
Public-facing, secured and scalable Simulation/Inference-as-a-Service cloud offerings
-
MLOps and CI, guide numeric studies requirements & implementations
-
Security, Federation, Billing integration
Work with Product Management on product offering strategy.
Defining requirements for training and inference datasets. Working with legal team on validating licenses and data's acceptable usage.
Defining product/service lifecycle: versioning, synchronization of release cycle with partner-teams, backward compatibility, reviewing documentation.
Represent Esri and the team at internal, international, and third-party scientific and industry events. Do presentations, lead and contribute to scientific publications, podcasts, write blogposts and journal articles.
Stay current on latest SOTA developments in traffic simulation, street optimization & generation, generative neural networks across multiple domains: graphs, raster, meshes & GS, point clouds, VLM/LLM, foundational geospatial models, etc. Collaborate with other researchers and developers within and across the teams throughout the R&D process.
Requirements
-
5+ years of professional software development experience working with C++ and/or Python
-
Demonstrated experience with R&D in multimodal (vehicular, pedestrian, public transportation, robotics, etc.) traffic simulation and optimization at macro, meso and macro levels
-
Knowledge of and willingness to continue developing expertise in the following areas:
-
Traffic Simulation & Optimization: Traffic simulation packages; ML-based optimization methods
-
Machine Learning & AI: PyTorch; GANs; Graph Neural Networks; autoregressive and sequence-to-sequence models; foundational LLMs and VLMs; multimodal shared embedding models
-
Software & Infrastructure: Ubuntu; Docker; cloud computing and model deployment/serving
-
GIS & 3D Modeling: CityEngine; ArcGIS Pro; ArcGIS Server; geoprocessing services
Strong analytical problem-solving skills and research experience in relevant fields
Excellent written and verbal communication skills
Bachelor's degree in computer science, data science, mathematics, robotics, remote sensing, computer vision or a related field
Existing work authorization in Switzerland
Recommended Qualifications
- Scalable CPU- and GPU-based processing of large volumes of spatiotemporal data
- NVIDIA RAPIDS, NVIDIA Kaolin, PyTorch Geometric
- Leading roles in research of software development groups
- Master's degree or higher in computer science, data science, mathematics, robotics, remote sensing, computer vision or a related field