We're looking for an experienced data engineer to own our science and modeling platform. You will own the platform that powers our data science, model training and evaluation, and API's E2E.
What You'll Do
- Build infrastructure to train and evaluate a variety of models
- Build tooling to normalize data, data pipelines, feedback infrastructure
- Stand up the API's used for production prediction and modeling
- Evaluate and improve model selection algorithms
- Deploy algorithms and models to improve prediction and ranking performance
- Generalize model training to include diverse data stores
- Develop, scale, and maintain our distributed systems
- Participate in the pizza production process
This role has the potential to evolve into a lead role as the team grows. It is located in Seattle, WA.
WHO YOU ARE
A generalist in data engineering and data science experienced in building production applications for data science and machine learning.
- Degree Computer Science or other technical degree and equivalent work experience
- Experience with Hadoop, Cosmos, Spark, or the equivalent
- Understanding and familiarity with common ML techniques. Deep knowledge of optimization, stochastic processes / markov chains, or the like a plus
- Software development experience in Python
- Familiarity with hardware / robotics
- Understanding of supply chains and/or operations
- Graduate course work in Optimization
- Previous experience at a startup