Data Scientist - Mapping

Responsibilities

• Design and build a high-quality, large-scale mapping dataset and data pipelines for training and evaluating machine learning models
• Design and build tools for model performance benchmarking and introspection
• Collaborate closely with machine learning engineers to define and refine data curation and model training strategies that drive measurable improvements in model accuracy and performance
• Collaborate cross-functionally with teams working on perception, planning, prediction, simulation, etc.

Requirements

• BS or MS in Computer Science or related field and 3+ years of experience
• Proficient in Python
• Strong Statistical Foundations: Deep understanding of hypothesis testing, experimental design, regression analysis, non-parametric/resampling methods (e.g., bootstrapping, permutation tests), and time-series analysis handling autocorrelated data
• Experience with large-scale, multi-modal datasets, benchmarking and introspection
• Ability to identify, clean, and process datasets containing high levels of noise or ambiguous classifications

Nice-to-Haves

• Experience in computer vision, machine learning algorithms
• Knowledge of geospatial data and coordinate systems
• Ability to write highly complex, optimized SQL queries for massive distributed databases
• Databricks experience