Senior Data Scientist

About the role

We are seeking a Senior Data Scientist to join our innovative team. In this role, you will focus on improving the accuracy of the Fingerprint Pro Identification Service by applying advanced data science and machine learning techniques in a high-load real-time service setting.

As a Senior Data Scientist, you will lead technical strategies, and contribute to fostering an engineering-focused, data-driven culture across the Fingerprint team. You will own data science projects from concept to deployment, ensuring they seamlessly integrate with our real-time identification platform.

Responsibilities:

Develop data-driven algorithms for the Fingerprint Identification Service, applying ML techniques to raw, noisy, and unlabeled data to extract insights about browsers and devices.
Lead the design and implementation of supervised, semi-supervised, and unsupervised learning approaches to improve our identification capabilities.
Own data science projects end to end, from concept and experimentation through deployment into our real-time platform.
Design experiments and solutions for ML engineering challenges such as real-time model inference and training pipeline automation.
Conduct exploratory data analysis to investigate ad-hoc questions and address anomalous data.
Help build an engineering-focused, data-driven culture across the team by sharing tools and effective approaches to data science.
Participate in a shared on-call rotation. Schedules are communicated in advance, and we balance coverage equitably while minimizing off-hours disruption.
This role includes participation in a shared on-call rotation. The schedule will be communicated in advance, and we strive to balance coverage equitably while minimizing off-hours disruptions.

Qualifications:

5+ years of experience across machine learning, data science, and backend development.
Advanced foundations in machine learning and statistical methodologies.
Strong experience with supervised learning, including gradient boosting and handling high-cardinality categorical data.
Practical experience with semi-supervised and unsupervised learning techniques.
Proficiency in exploratory data analysis, and creative problem-solving for dataset collection and performance estimation in the absence of labeled data.
Strong expertise in real-time ML service development, including real-time inference and model-to-service integration.
Ability to turn ML models into MVP real-time web services.
Excellent coding skills, including SQL and general software engineering tools (Git, CI/CD pipelines, IDEs, shell scripting).
Fluent English for clear communication in a global, remote team.

Nice to have:

An academic background and a research mindset.
Backend development experience with Go.
Experience with analytical storage systems such as ClickHouse, Snowflake, or BigQuery.
Familiarity with engineering practices for maintaining data transformations, including frameworks like dbt.
Hands-on experience with data visualization tools such as Apache Superset, Tableau, or Looker.
Hands-on experience with vector databases (e.g., Pinecone, FAISS, Qdrant).
Experience building and maintaining embedding-based search systems.

Technologies you'll work with:

Backend and data science: Go, SQL, and advanced ML frameworks
Data processing and analytics: ClickHouse, dbt
Infrastructure: AWS