edrone

Data Scientist

Job description

edrone is an Autonomous eCommerce Cloud, is the first eCRM designed for eCommerce. We provide advanced Marketing Automation solutions, based on our algorithms, that are easy to install (Plug'n'Play). Our goal is to help to understand customers behavior (Customer Intelligence) and engage them (Marketing Automation) with an all-in-one e-commerce marketing cloud.

We're a hard-working, fun-loving, get-things-done type of team that is building a platform that helps increase client’s online sales. We know how much grit it takes to start your own business and grow it into something that lasts. We roll our sleeves up, we act fast, and we learn together. We're looking for people that will do the same.


Responsibilities

  • Creating new solutions based on data

  • Developing and maintaining ML models

  • Preparing reports/visualizations for Product Team

  • Building ETL pipelines

Skills - required

  • Experience in Python

  • Data Science

    • the ability to present the results transparently and clearly

    • focus on giving value to business

    • knowledge of A/B tests

  • SQL

    • experience in both Relational and NoSQL databases

    • ability to perform complex selects

    • preferably MySQL and DynamoDB

  • Machine Learning

    • knowledge of ML algorithms for recommendations, classification, regression, forecasting, clustering and when to use a given model

  • Practical knowledge of GIT

Skills - nice to have

  • Experience in deploying and maintaining ML models in production

  • AWS (Athena, S3, SQS, Lambda, RDS, DynamoDB, QuickSight)

  • Java

  • Basic knowledge of data processing pipelines

    • PySpark, EMR, Hadoop

  • Some experience with web development in Python ecosystem, e.g. Flask

  • Deep Learning experience with TensorFlow, PyTorch

  • Exposure to Continuous Integration/Continuous Deployment Environment

How we work

  • DevOps - you build it you run it

  • Small, tightly-knit groups of very skilled people

  • Code Reviews

  • Directly Responsible Individual

  • Pair programming

  • Paying back technical debt whenever you can

  • 1:1s

  • Blameless postmortems

What we value

  • Seeking mastery. We read books, attend conferences and meetups. We have a library of books. We study alone and in groups. Company has a budget to support us. We do this because it is our passion.

  • Curiosity. If we use something we want to know how it works exactly. What are the constraints, when does it fail

  • Direct, honest and timely feedback. This is how we improve.

  • Autonomy. We support each other and we actively avoid micromanagement.

  • Being a good human. We don’t tolerate jerks, no matter how brilliant they are


Interesting technical challenges

  • Scalability - we ingest “tons” of data that must be processed near-real time. Traffic patterns change constantly and we have to adapt dynamically. We rely on horizontal partitioning and auto-scaling a lot.

  • Reliability - uptime, latencies, queue processing delays - we live and breathe by these metrics. We assume machines, disks, network and software will fail. Our approach is resilience engineering and automation.

Other tech we use

  • AWS (25+ services) Java 11, git, JIRA, Confluence, WebStorm, PhpStorm, IntelliJ, Redis, Hadoop, Spark



Zakres obowiązkówPoszukiwane kompetencjeOferujemy

Please let the company know that you found this position on this Job Board as a way to support us, so we can keep posting cool jobs.