Prediction Markets Quantitative Engineer
Cross-asset quantitative trading firm providing liquidity, treasury management, and institutional advisory services across currencies, crypto, commodities, and derivatives.
About G-20 Group
G-20 Group states that it was established in 2010 and operates globally across delta-one and derivatives markets. Its services include liquidity provision and market making across exchange-traded and on-chain venues, treasury management, and advisory services covering growth, liquidity, token design, go-to-market strategy, treasury management, and M&A. It also invests across infrastructure, DeFi, stablecoins, and AI-driven technologies.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
Build research and trading infrastructure for prediction markets across multiple venues, including probabilistic forecasting models, pricing and edge frameworks, arbitrage strategies, risk frameworks, data pipelines, execution tooling, monitoring, reproducibility, and governance.
Requirements
- Degree in Quantitative Finance, Mathematics, Computer Science, Statistics, or a related quantitative field.
- Strong Python engineering skills and experience with production systems and data engineering.
- Solid foundation in statistics, probability, and machine learning.
- Experience building backtests and evaluating predictive models with appropriate metrics.
- Familiarity with expected value, position sizing, risk budgeting, correlation, and liquidity constraints.
- Ability to communicate clearly about model assumptions, limitations, and risk.
- Schedule flexibility around major event windows.
- Self-motivated, detail-oriented, and comfortable in a dynamic startup-like environment.
Responsibilities
- Develop probabilistic models to forecast real-world events.
- Combine heterogeneous signals into calibrated probability estimates.
- Build pricing, edge, uncertainty, and model-drift frameworks.
- Design evaluation methods using proper scoring rules, calibration curves, and realistic back-tests.
- Identify mispricings and design arbitrage and relative-value strategies.
- Build position sizing, risk, and portfolio optimization frameworks.
- Build data pipelines and real-time services.
- Implement execution tooling, monitoring, and automated safeguards.
- Create dashboards and alerts for performance, exposure, model health, and operational integrity.
- Ensure reproducibility through experiment tracking, model registries, CI/CD, and robust testing.
- Collaborate with trading, risk, and compliance stakeholders.
- Document models, assumptions, failure modes, and operating procedures.