Data Scientist

Description

At SWAG Live's data team, our mission is to democratize data by building a self-service data platform. We aim to empower internal teams to access, interpret, and derive valuable insights from data effectively.

As a Data Scientist in this role, you will collaborate with a multidisciplinary team of engineers and analysts to tackle diverse challenges using quantitative techniques such as statistical analysis and machine learning. You will work with large, complex event-based datasets, conduct exploratory data analysis (EDA), define requirements, and develop & deploy models. We are particularly seeking a data scientist with experience in building customized recommendation models and a strong interest in product-focused machine learning development.

Responsibilities

- Leverage state-of-the-art algorithms to build fully customized recommenders and other growth models.

- Design, deploy and maintain all components necessary for modeling, including feature engineering, automatic model training & tuning and engineering toolchains.

- Create a comprehensive monitoring framework to evaluate model performance and provide actionable insights to drive business growth, focusing on awareness conversion and transactions.

- Understand stakeholder business requirements and design end-to-end machine learning/AI solutions that are effective, practical, and robust in addressing business challenges.

- Collaborate closely with data engineers and backend engineers to develop scalable systems.

- Communicate efficiently with cross-functional teams, promote the implementation of strategic applications, and drive continuous optimization.

Requirements

- 3+ years in at least one of the following areas: search, recommendation systems, ads, content understanding/moderation, or anti-fraud.

- Solid experiences in Python and related Data Analysis libraries (e.g., pandas, numpy, matplotlib, scikit-learn).

- Proficient in at least one Deep Learning framework (e.g., TensorFlow, PyTorch, Keras, Theano).

- Familiarity with Big Data tools such as Ray, Hive SQL, Spark, or MapReduce.

- Strong understanding of the software development lifecycle and low-level code optimization.

- Solid theoretical foundation in commonly used algorithms and strong statistical intuition.

- Excellent communication and collaboration skills; ability to explore new technologies with the team and drive technical innovation.

- Highly curious, self-motivated, and eager to take on challenges and strive for excellent.

Good to have

- Prior experience in large-scale recommendation systems or search engines.

- Familiarity with deep learning-based recommendation models such as DLRM, BERT4Rec, and NCF.

- Experience with API service development and deployment.

- Experience working with GCP and containerization technologies.

- Expertise in building LLM applications and working with foundational models (e.g., LLaMA, GPT) and frameworks like LangChain and Weights & Biases.