Please Note: This is a hybrid role based in Utah—only local applicants will be considered. If you're open to relocating, please let us know in your application.
About Smule
At Smule, we don’t just build apps—we build connections through music. Join a team where your work will inspire millions to create and collaborate. Be part of a global movement that turns musical dreams into reality
About The Role
We're looking for a Data Scientist to help take our product and analytics capabilities to the next level. You'll join a lean, cross-functional data team where you'll work across the full stack, from deep user analysis, KPI development, and A/B testing to building ranking models that power personalized user experiences.
Our team includes experienced ML and BI Engineers and Analysts, and reports directly to the Director of Data. We're collaborative, fast-moving, and deeply connected to the product: we're responsible for everything from executive reporting to developing machine learning models that improve user engagement and satisfaction. You'll operate across this full stack, supporting product discovery through deep user and business analysis, helping define and test success through experimentation, and building embedding-based retrieval, re-ranking, and recommendation systems.
This role is ideal for someone who thrives at the intersection of data science, product thinking, and engineering: someone who is excited to drive impact from prototype to production.
Product & Experimentation Support
- Work closely with Product to define success metrics, analyze user behavior, drive A/B tests and interpret their results.
- Contribute to the design of controlled experiments, including power analysis, segmentation, and instrumentation planning.
- Partner with PMs in an assigned squad to monitor KPI health post-release and continuously iterate on the product with a bias for impact.
- Maintain (or occasionally build) Tableau dashboards and internal metric frameworks that help teams inform their decisions.
Search & Recommendation Systems
- Work alongside ML Engineers to move promising prototypes into production, contributing features, evaluation logic, and model tuning strategies.
- Help design and iterate on a hybrid retrieval-reranking pipeline, combining lexical scoring (e.g. BM25) with embedding-based similarity (semantic vectors).
- Train and evaluate models that embed user queries and catalog items into a shared vector space using tools like SBERT, CLAP, or custom transformer heads.
- Contribute to ANN-based retrieval (e.g. FAISS, HNSW in Elasticsearch) and deep re-ranking models that improve content relevance and personalization.
- Collaborate with ML Engineers to maintain and improve existing recommendation systems
Modeling & Personalization
- Develop models for user segmentation, content affinity, churn prediction, and lifecycle modeling — using statistical or ML approaches as appropriate.
- Partner with ML Engineers to validate offline performance, manage feature versioning, and test production models through staged rollout or shadow deployment.
- Investigate and prototype embedding-based re-rankers, user profile vectors, and intent prediction models to increase downstream engagement.
Data Infrastructure & Collaboration
- Partner with BI Engineers to improve our analytics layer (Airflow, dbt), enhance schema design, and automate recurring data quality checks.
- Write modular, maintainable code in Python for analysis, modeling, and batch/real-time inference tasks.
- Contribute to shared libraries or internal packages for metrics, feature engineering, or evaluation logic.
About You
- 3+ years experience in a data science, applied ML, or product analytics role
- Bachelor’s degree in statistics, mathematics, computer science, or related field (Master’s or PhD preferred)
- Understanding of experiment design, including segmentation, causal inference, or uplift modeling
- Strong communication skills and ability to work with stakeholders across engineering, product, and executive functions
- Strong SQL and Python skills — you’re comfortable writing complex joins, CTEs, and analytical functions in SQL, and working with Pandas, Scikit-Learn, and PyTorch.
- Experience with search, recommendations, or retrieval-based ranking systems, including familiarity with:
- Lexical vs semantic retrieval tradeoffs
- Query/item embeddings
- ANN search and vector indexing (e.g. FAISS, HNSW)
- Ranker evaluation (MRR, nDCG, recall@k)
- A working understanding of how embedding similarity integrates with lexical ranking (e.g., hybrid scoring, reciprocal rank fusion, weighted sum).
- Familiar with the modern data stack (Snowflake, dbt, Airflow, Tableau), and capable of working across it to support both analysis and production ML workflows.
Nice to Have
- Experience with embedding models like SBERT, CLAP, MuLan, or fine-tuning transformer architectures for domain-specific tasks
- Familiarity with model monitoring, version control for ML artifacts, and deployment pipelines
- Prior experience with music/audio tech, content platforms, or recommendation-heavy consumer products
Why This Role?
- Real Impact: You’ll work on features directly tied to user experience and platform growth, including smarter discovery, personalization, and lifecycle touchpoints.
- Technical Breadth: From dashboards to deployed ranking models, you’ll touch the full stack of data work in a fast-paced, creative environment.
- Growth Opportunity: You’ll be supported by the Director of Data and have the freedom to grow your role toward product analytics, engineering, or modeling specialization, based on your strengths and interests.
Why Smule?
- Collaborate with a global team passionate about music and innovation.
- Work on exciting projects that shape how millions connect and create.
- Be part of a company that values creativity, curiosity, and impact.
Ready to turn data into harmony? Apply today and let’s make music together!
Smule is an Equal Opportunity Employer
We celebrate diversity and are committed to creating an inclusive environment for all employees. We welcome applicants from all backgrounds and experiences, and we evaluate all qualified candidates without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other legally protected status. If you need assistance or an accommodation during the application process, please contact us
