Senior Data Scientist

Role overview

A Senior Data Scientist opening on a team building real-time device intelligence that helps enterprises detect and stop online fraud. The work blends applied machine learning research with production-grade engineering in a high-load, low-latency environment. The position is fully remote within a globally distributed organization.

Responsibilities

- Build ML algorithms that extract insights from raw, noisy, and unlabeled browser and device signals - Lead the design of supervised, semi-supervised, and unsupervised learning approaches to sharpen identification accuracy - Drive data science initiatives from initial concept and experimentation through deployment into a live inference platform - Tackle ML engineering problems such as real-time model inference and automated training pipelines - Run exploratory analyses to investigate anomalies and answer open-ended questions - Help cultivate a data-driven engineering culture by sharing tools, methods, and best practices - Take part in a shared on-call rotation with predictable scheduling and balanced coverage

Requirements

- 5+ years of combined experience in machine learning, data science, and backend development - Solid grounding in ML theory, statistics, and experimental design - Strong supervised learning skills, including gradient boosting and high-cardinality categorical features - Practical experience applying semi-supervised and unsupervised learning methods - Comfort designing creative approaches to dataset construction and performance estimation when labels are scarce - Track record building real-time ML services and integrating models into production web services - Strong coding ability in SQL plus modern engineering tooling (Git, CI/CD, IDEs, shell) - Fluent English for clear communication across a distributed team

Nice to have

- Academic or research-oriented background - Backend experience with Go - Familiarity with analytical stores like ClickHouse, Snowflake, or BigQuery - Experience maintaining data transformations with frameworks like dbt - Hands-on work with visualization tools such as Apache Superset, Tableau, or Looker - Experience with vector databases (Pinecone, FAISS, Qdrant) and embedding-based retrieval systems

Benefits and work setup

- Fully remote role within a globally distributed team - Inclusive culture that actively welcomes candidates from underrepresented groups in tech - No visa sponsorship; candidates must be authorized to work from their home location