We’re looking for a Machine Learning Engineer to come and join our team, to help us build upon and improve our systems that help connect our customers who love fashion with the world’s top fashion brands.
Lyst is a Global Fashion Search Platform which connects millions of shoppers globally with the world’s leading fashion designers and stores, giving them a simpler, more engaging buying experience.
Lyst itself is divided into tribes, then into smaller product-led teams. We work in a similar way to the Spotify model, having tribes that contain small multi-disciplinary teams that have all the skills they need to deliver the team goals. Each team is responsible for the deployment and operation of the software they work on.
About the team:
- We maintain about half a dozen services with a team of 5 engineers, 2 data scientists and our product manager.
- We care about collecting metrics and properly monitoring our services.
- We work mostly in Python3.
- We use Docker and Empire for managing our services in production.
- We use CircleCI for continuous integration and moved a lot of our services to be continuously deployed too, which is exciting!
- We report to the VP of Engineering, who in turn reports to the Executive Team
- We work closely with other teams across tribes, and almost all of Lyst engineering uses our services.
- We have 2 week sprints, use JIRA and Slack, and hold daily standups.
About the role:
As a Machine Learning Engineer at Lyst, you’ll be working on one of the teams responsible for making connections between products and our customers, happen. You'll be working on problems involving named entity recognition, search result ranking & diversification, personalisation and recommender systems in order to improve our product.
We solve some unique problems at Lyst, with the largest data catalog of fashion products, you’ll be learning the best solutions as you go. We aim to build software that’s easy to maintain and low on surprises, which is a goal in many of the design approaches we’ve taken.
You’ll have the opportunity for impact by helping teach other engineers new techniques and applications, while collaborating with product managers to help find new ways to apply data science and machine learning in our solutions.
We have a data science chapter, where we hold regular literature reviews and data science training sessions to help spread knowledge of the best techniques available that fit our problem.
- Experience with the creation and maintenance of ETL pipelines
- Comfortable with large datasets
- Contribute to an inclusive and positive working environment for everyone
- Being able to communicate clearly and be humble when sharing ideas with everyone on the team
- Capable of writing production code and doing iterative development, balancing speed to ship and long term maintainability
- Have a detail oriented mindset and actively demonstrates curiosity
We make great use of both the Python and AWS data science ecosystems to power our solutions. Familiarity with Jupyter, Pandas, PySpark, Sagemaker, Tensorflow and related tools would be helpful.
If you’ve programmed in a different language and not done Python before, that’s OK, knowing how to code is a transferable skill. Equally if you’ve never used AWS before and have experience of an alternative cloud provider, that’s OK too. There’s time to learn on the job and a supportive, knowledgeable team will help you.
We believe in having a curious mindset and your ability to learn to do the job, rather than a checklist of must haves.
Closing Date - 23rd October 2019