9 hours ago
Stockholm, SwedenSenior / Staff+
Responsibilities
- Take machine learning models from training through production, including data pipelines, training, evaluation, and serving.
- Determine model placement and GPU scaling while setting latency and cost targets.
- Build evaluation systems covering precision, recall, threshold calibration, labeling, quality assurance, and online validation.
- Develop and measure AI quality agents that identify and fix product catalog errors.
- Monitor production changes and explain model decisions to backend, operations, and product colleagues.
- Contribute to product matching, attribute enrichment, multimodal modeling, and catalog quality systems.
Requirements
- Experience taking ML models from training to production in a live system.
- Hands-on deep learning experience.
- Production-quality Python development, including testing, code review, and containers.
- Strong ability to measure model performance and select appropriate metrics and thresholds.
- Experience with LLMs and reasoning about quality, cost, and latency trade-offs.
- Clear communication with backend, operations, and product teams.
- Preferred experience optimizing GPU inference with Triton, TensorRT, or similar tools; training deep learning models at scale; working with multimodal image-and-text models; building LLM agents with tool use; or creating ML pipelines from scratch.
Benefits
- Based in Stockholm and working with a six-person data science and ML engineering team collaborating across Europe.
- Applicants should provide a CV in English.
Tech Stack
Apache HivePython
Categories
About Klarna
Klarna is a privately held fintech that provides buy now, pay later financing, checkout, and a consumer shopping app for e-commerce and retail. It monetizes through merchant fees, interchange, and interest and fees on financing, while offering marketing and customer acquisition tools to merchants. Founded in 2005 and headquartered in Stockholm, it operates across Europe and North America.