Pecan is an automated AI-based predictive analytics platform. It simplifies and accelerates the process of building and deploying predictive models in various business use-cases, such as life-time value, Churn, demand forecast and more. Pecan connects to the raw data and completely automates the data preparation, engineering and prepossessing phases, as well as the model training and evaluation lifecycle. It was acknowledged as one of Israel's 50 most promising startups two years in a row.
What will you do?
Work on pecans’s data and machine learning infrastructure, which is at the heart of Pecan's offering. You will create innovative solutions for data ingestion and normalization from multiple data sources, as well as feature engineering and feature selection for our ML models. You will also design and implement technology solutions to protect Pecan's customers data and privacy, using rigorous data isolation and security technologies - such as de-identification pipelines, data obfuscation etc.
Who You Are & What We're Looking For
- 3+ years experience as a Machine Learning Engineer
- 5+ years of experience with Python/Java/Scala
- Strong understanding of distributed systems, object-oriented programming and design patterns
- Hands-on experience with open source ML libraries like: catboost, lightgbm, xgboost, scikit-learn, shap etc’.
- Microservices architecture, cloud technologies, Docker/K8s
- Ability to design and own a feature through all its phases
- Hands on experience with Spark, SparkSQL, Spark streaming and other Spark related projects
- Building data pipelines using Apache Airflow
- B.Sc. or higher in Computer Science or a similar