Senior Data / ML Engineer

Senior Data / ML Engineer

This job is no longer open
Minimum qualifications
• Thorough understanding of at least one modern programming language (at Hopper we use mostly Scala and Python)
• 4+ years professional experience in data engineering capacity with experience designing and building ETL pipelines
• Expertise with deduping data, and web scraping
• Experience working in a cloud environment with data warehouse technologies such as BigQuery, Redshift, Athena, or Snowflake
• Excelled in an environment with cross-functional teams, working fluidly with Product Managers, Data Scientists, Software Developers, and other highly skilled specialists
• Exposure to data-intensive systems as well as writing production-quality software

Preferred qualifications
• Experience with, or willing to learn, distributed system development in Scala
• Thorough understanding of data engineering, designing and building data pipelines at scale
• Experience in Recommendation Systems and Feeds-ranking a strong plus
• Experience with data parsing, transformations, normalization, loading, and storage
• Experience with data streaming technologies such as Apache Kafka, Google Pub/Sub, or Amazon Kinesis
• Proven track record of leading less-experienced engineers in building stable and scalable production quality code 
• Proven ability to build prototypes and take a data-driven approach to product development, testing and measuring new ideas very quickly
• The ability to bring leading industry techniques and technologies to the table

About the job 
As a Senior Data Engineer on the Homes team, you’ll have the opportunity to work on a greenfield product within Hopper’s $1B+ travel ecosystem.  You’ll work alongside a talented and experienced team of developers, designers, and travel industry experts to bring Hopper’s travellers the best price, selection, convenience, and booking flexibility in home rentals. In tandem with Data Scientists, you will be a trusted partner in building out critical components for extracting and ingesting data from websites using scraping tools. You will own the creation of these tools, services, and workflows and we will rely on you to test and ensure accuracy and quality. These tools will be critical to the success of the Homes team as it will ensure that our customers are guaranteed the lowest price for their vacation rental. 

Responsibilities

    • Design and implement a process to systematically match a vacation rental property listing across all major OTA vacation rental sites to enable price comparisons and price matching
    • Write and execute web scraping tools for data collection to ensure Hopper offers the best possible price to customers
    • Test, build, maintain and continually improve matching algorithms using a combination of backend property IDs from existing supplier APIs, combined with data from third-party rental analytics platforms and web scraping (methodologies could include ML on images, description matching, address parsing, map matching, and a manual review option)
    • Collaborate with data scientists and product managers in creating dynamic pricing models to accurately predict if vacation rental prices will increase or decrease, leveraging existing databases for forward-availability as well as Hopper’s own flight data 
    • Quickly prototype new ideas and run experiments to determine the next set of data driven features to build for Hopper Homes customers
    • Help shape the systems design for price matching and how it integrates with our microservices architecture
    • Collaborate with a diverse group of people, giving and receiving feedback for growth
    • A passionate focus on writing quality, testable, scalable code that performs well for our consumers

Our tech stack

    • We have a microservice architecture with over 200+ services.
    • Mostly Scala on the backend with some Python.
    • Our UIs are Mobile first: Swift on iOS and Kotlin on Android.
    • We mostly host our services on Google Cloud with some on-prem.
    • We use things like HBase, Kafka, Pub/Sub, GCP Big Query, Cloud SQL, S3, Delos, Redis.
    • We are driven by data so Amplitude, Big Query and Datadog will be your buddies.

Benefits

    • Well-funded and proven startup with large ambitions, competitive salary and stock options
    • Unlimited PTO
    • WeWork All Access Pass OR Work-from-home stipend
    • Entrepreneurial culture where pushing limits and taking risks is everyday business
    • Open communication with management and company leadership
    • Small, dynamic teams = massive impact
    • 100% employer paid medical, dental, vision, disability and life insurance plans
    • Access to a 401k 
More about Hopper
Today, Hopper is best known as a travel app. We're going to do about $1B in sales this year and weathered the COVID storm better than anyone expected. We just raised $170M from Goldman Sachs and Capital One, and inked a deal to be the exclusive travel provider for Capital One Travel.

We owe our success, in large part, to a proprietary suite of data-driven and risk-based financial services that we have developed that complement a customer's trip-purchasing experience. One example is Price Freeze, where our customers are able to purchase a financial option in the app to lock in any price that they see, on any item, for as short as 1 hour or as long as 21 days with Hopper taking the risk on the other side of the trade.

Now we're laying the groundwork for continued expansion in 2021 by adding great people to our team who can help us compete with the travel giants.

#LI-Remote
This job is no longer open
Logos/outerjoin logo full

Outer Join is the premier job board for remote jobs in data science, analytics, and engineering.