remote
Full-Stack Data Scientist - Nimbus
Data Scientist
Full-Stack Data Scientist driving end-to-end ML solutions on AWS, building scalable data pipelines and production-ready models that power real‑time ad delivery and platform optimization.
About the role
Key Responsibilities
- Design, develop, and maintain end‑to‑end data pipelines on AWS, ensuring high throughput and low latency for real‑time ad decisioning.
- Build and deploy production‑ready machine learning models using Python, integrating them into the existing backend stack.
- Collaborate with backend engineers to architect scalable microservices that expose model predictions to the ad delivery engine.
- Monitor model performance, troubleshoot data quality issues, and iterate on feature engineering to improve accuracy.
- Document data workflows, model assumptions, and deployment procedures for cross‑team transparency.
Requirements
- Strong experience with Python, AWS services (S3, Lambda, SageMaker, Glue), and data engineering best practices.
- Proven track record of deploying machine learning models into production at scale.
- Solid understanding of backend development, RESTful APIs, and microservice architecture.
- Excellent problem‑solving skills and ability to work in a fast‑paced, high‑volume environment.
Skills
pythonawsmachine learning