Senior Machine Learning Engineer

Description

As a Senior Machine Learning Engineer, you will be responsible for developing and maintaining the fit and sizing models that form the backbone of our services. Our product offerings, powered by machine learning, are integrated into the largest fashion and apparel e-commerce stores in the US and Europe and provide shopping experiences that revolutionize online commerce. Your work will directly impact our 50+ million users and ensure their happiness.

We are looking for someone who is ready to tackle any/all parts of the machine learning pipeline. In this role, you will analyze large sets of behavioral and product attribute data from data preparation to productionizing ML models and prediction. You will propose novel ML and sometimes non-ML solutions to business problems, develop, test, and present your solutions. Your responsibilities will also include productionizing data preparation, modeling, prediction, and monitoring.

What you'll be doing

• Participate in product discussions, propose and test solutions to business problems
• Design, build and maintain production machine learning models and pipelines
• Work closely with data and backend engineers to serve predictions, support new products/features, etc.

Who you'll be working with

• A small, but clever team of data scientists, who design new products from scratch
• Our leadership and product team members who will provide you with an unlimited supply of exciting challenges to tackle
• Our highly capable engineering team that maintains robust scalable data pipelines and supports low latency prediction serving

The majority of our team is located in Budapest, Hungary, but you'll be able to work remotely anywhere in the EU. #LI-remote

Requirements

As a senior member of a small team, you will have a great influence on the design of SSP’s products. Accordingly, we are looking for someone with hands-on experience building production machine-learning solutions from the ground up. In particular, your experience should include typical data science tasks (e.g. idea generation, data manipulation, modeling, model comparison, etc.) as well as basic engineering (e.g. writing clear maintainable code, building data or feature engineering pipelines, maintaining scripts and tooling to support ML tasks and deployments, performing predictions at scale, etc.).

We appreciate if you have the following  experiences

• Strong background in machine learning and related programming (preferably in Python)
• Hands-on experience productionizing machine learning models/pipelines and a solid understanding of best practices
• Experience with feature engineering and common machine learning algorithms (e.g. Regression, GBM, ANNs, etc.) including knowledge of hyperparameter tuning, regularization, etc.
• Familiarity with general backtesting strategies as well as time-series-specific techniques
• Strong programming background including collaborative coding with version control, unit, and integration testing
• A deep understanding of the utility and limitations of various model evaluation metrics for both online and offline environments
• Ability to stay up to date with ML techniques and libraries and to acquire any missing technical skills concurrently while executing on projects
• Basic data visualization experience to support explanations of problems/solutions

The soft skills that we think are important

• Clearly explain problems, present solutions, and debate strategies in English to both technical and non-technical audiences
• Understand a business problem, then propose and weigh multiple solutions
• Collaborate effectively with Data Scientists, Engineers, and Product Team members
• Estimate and plan machine learning projects and coordinate with engineering team members

Bonus points

• Advanced training in ML, Statistics, CS, or a related discipline (Masters, PhD preferred)
• Experience with A/B testing as a form of model evaluation
• Hands-on experience with PySpark and/or Databricks
• Experience handling unstructured text and/or NLP methodology
• Experience building tooling, scripts (e.g. bash, python, etc), or systems to support ML investigations, deployments, etc.
• Monitoring production model performance using automated dashboards or data visualization
• You are active on GitHub and have contributed to open-source projects

If the role sounds interesting, apply now and get to know us during the interviews. You can read more about our hiring process on Glassdoor.