Essential functions: 

• • Optimize the team’s algorithms for deployment 
• • Develop transportable and customizable SDKs for our core algorithms, allowing them to be plugged into any of our apps 
• • Develop SDKs for rapid prototyping and deployment of algorithms 
• • Automate and orchestrate advanced split tests of models 
• • Continually refine the department’s code base and ensure best development processes 
• • Identify constraints, strengths, and weaknesses of technology options for each algorithm 

 

Skills: 

• • Expert in distributed computing with Spark, DevOps best practices, and containerization 
• • Expert coding ability in Python and high competency with PySpark 
• • Understanding of, and experience productionizing, the following ML concepts: o Collaborative filtering 
• o Matrix factorization 
• o Ranking algorithms 
• o Advanced regression, classification, clustering, and time series algorithms 
• o Automated hyperparameter tuning and model selection 
• o Deep learning at scale for NLP 
•  
• • Experience with advanced search concepts using deep learning is a plus! 

 

Experience: 

• • 3 + years of applied Machine Learning experience 
• • 2 + years of experience deploying, scaling, monitoring, and continually improving algorithms 
  • • Experience deploying models on very large data using: o Spark, MLlib, PySpark, Scala 
  • o Kafka 
  • o Kubernetes, Docker, containerization 
  •  
  • • Knowledge of model management 
  • • Knowledge of API development best practices