Quantitative betting models and real-time trading infrastructure
White Swan Data operates a quantitative betting business with a technical stack built for low-latency execution: Python, PyTorch, TensorFlow, GCP, and Docker underpin their trading pipelines. The project roster reveals a dual focus on improving internal systems (trading pipeline optimization, millisecond-latency infrastructure) and expanding capability (visual data processing via ComfyUI and OpenCV, multi-source data ingestion). Engineering dominates the hiring mix, with mid-level practitioners being recruited to handle both model refinement and operational scaling.
White Swan Data is a London-based quantitative betting firm using mathematical models and algorithmic trading to identify and exploit opportunities in betting markets. The team combines mathematicians, data scientists, and software engineers working across three overlapping domains: betting strategy, quantitative research, and production systems. Over 15 years, their technology has generated consistent returns for clients. Current operational priorities include optimizing trading pipelines for millisecond latency, managing downtime risk, and scaling data ingestion from multiple sources. The company is actively hiring across engineering, operations, and management roles in the UK, Ireland, and Italy.
Python, PyTorch, TensorFlow, GCP, Docker, Java, C++, Node.js, SQL, plus OpenCV and ComfyUI for visual data processing workflows.
Real-time trading systems, low-latency data processing pipelines on GCP, advanced automation with visual data workflows, multi-source data scraping, and sports betting models (including football).
Other companies in the same industry, closest in size