hybrid
Senior Data Scientist, Cost Prediction
Senior Data Scientist, Cost Prediction
Xometry is hiring a Senior Data Scientist to join their cost prediction team, focusing on developing and optimizing predictive models using machine learning techniques and 3D data. The role involves data preparation, analysis, and utilizing cloud resources to inform business strategy within a fast-paced environment.
About the role
About the Role
Xometry is looking for a Senior Data Scientist to join their cost prediction team. This role is ideal for a candidate passionate about applying machine learning tools and techniques to construct, optimize, and evaluate predictive models. The successful candidate will focus on predicting various business outcomes and utilize their expertise in probability and statistics to derive defensible statistical inferences from data, especially leveraging 3D data.
Responsibilities
- Develop effective predictive models using data science and machine learning principles, specifically with 3D data.
- Write software for data preparation, cleaning, and sampling to support predictive model development.
- Utilize cloud resources, particularly Amazon Web Services (AWS), for data preparation and processing.
- Query and extract data from databases, including Snowflake and MongoDB.
- Employ data analysis and visualization tools such as SQL, Python, Jupyter Notebooks, and Looker to inform business strategy.
- Iterate solutions rapidly within a fast-paced and often ambiguous environment.
- Tackle challenging and uncharted problems.
- Contribute to a team-oriented environment that prioritizes continuous learning.
Requirements
- Bachelor’s degree required; a degree in applied math, computer science, natural sciences, or engineering is preferred.
- M.S. or PhD in a related field is highly desired.
- 5+ years of experience in machine learning, statistical modeling, and optimization techniques.
- 2+ years of experience in 3D deep learning, specifically with Mesh, Volumetric, and/or Point Clouds.
- Fluency in Python, with a preference for experience in libraries such as pandas, numpy, SciPy, and scikit-learn.
- Proficiency in linear algebra and statistics.
- Familiarity with scientific software principles, including versioning systems, reproducibility, and code deployment.
- Experience in the manufacturing industry is desired.
- Must be a US Citizen or Green Card holder (ITAR compliance).