At SWAG Live's data team, our goal is to democratize data by building a self-service data platform. We strive to empower our internal teams with the ability to access, understand, and generate valuable insights from data.
In this role, you'll work with a multidisciplinary team of engineers and analysts to solve a variety of problems using statistical methods. You'll handle large, complex event-based datasets, conduct comprehensive data gathering, specify requirements, perform exploratory data analysis, and develop models. We're particularly interested in a data scientist with experience in developing recommendation models and a keen interest in LLM product development.
Responsibilities
- Collaborate with the business intelligence team to utilize historical data in forecasting future trends and detecting fraud.
- Collaborate with the operations team and the data engineering team to design various systems, which include, but are not limited to:
- User activity monitoring and anomaly detection
- Content moderation system
- Systems for optimization operation workflows
3. Work with the data engineering team to design and implement recommendation systems at scale.
Requirements
- Fluency in common data science Python libraries, including but not limited to numpy, pandas, scikit-learn.
- Fluency in several machine learning frameworks, including but not limited to tensorflow / pytorch, keras, theanos, pyspark
- Proficiency in the basic software development lifecycle and low-level code optimization.
- A self-directed learning mentality.
- Comfortable working in an English-speaking environment.
Good to have
- Knowledge in deep learning based recommender system such as DLRM, Wide & Deep , and NCF.
- Expertise in building LLM applications and familiarity with foundational models (LLaMA, BERT, GPT, Mixtral 8x7B) and frameworks, such as langchain, weights & biases as well as retrieval mechanisms with vector databases such as pinecone and weaviate.
- Experience in leading a team and providing mentorship.
