Project description Lead the design and development of advanced quantitative and AI-driven models for market abuse detection across multiple asset classes and trading venues. Drive the solutioning and delivery of large-scale surveillance systems in a global investment banking environment, leveraging Python, PySpark, big data technologies, and MS Copilot for model development, automation, and code quality. Play a pivotal role in communicating complex technical concepts through compelling storytelling, ensuring alignment, and understanding across business, compliance, and technology teams. Responsibilities Architect and implement scalable AI/ML models (using MS Copilot, Python, PySpark, and other tools) for detecting market abuse patterns (e.g., spoofing, layering, insider trading) across equities, fixed income, FX, and derivatives. Collaborate closely with consultants, MAR monitoring teams, and technology stakeholders to gather requirements, share insights, and co-create innovative solutions. Translate regulatory and business requirements into actionable technical designs, using storytelling to bridge gaps between technical and non-technical audiences. Develop cross-venue monitoring solutions to aggregate, normalize, and analyze trading data from multiple exchanges and platforms using big data frameworks. Design and optimize real-time and batch processing pipelines for large-scale market data ingestion and analysis. Build statistical and machine learning models for anomaly detection, behavioral analytics, and alert generation. Ensure solutions are compliant with global Market Abuse Regulations (MAR, MAD, MiFID II, Dodd-Frank, etc.). Lead code reviews, mentor junior quants/developers, and establish best practices for model validation and software engineering, with a focus on AI-assisted development. Integrate surveillance models with existing compliance platforms and workflow tools. Conduct backtesting, scenario analysis, and performance benchmarking of surveillance models. Document model logic, assumptions, and validation results for regulatory audits and internal governance. Skills Must have Technical Skills: 7+ years of experience Investment banking domain experience Advanced AI/ML modelling (Python, PySpark, MS Copilot, kdb+/q, C++, Java) Must be well versed with SQL and have hands on experience writing SQL (preferably Spark SQL) that is productionized (not ad-hoc queries) for at least 2-4 years Familiarity with Cross-Product and Cross-Venue Surveillance Techniques particularly with vendors such as TradingHub, Steeleye, Nasdaq or NICE Statistical analysis and anomaly detection Large-scale data engineering and ETL pipeline development (Spark, Hadoop, or similar) Market microstructure and trading strategy expertise Experience with enterprise-grade surveillance systems in banking. Integration of cross-product and cross-venue data sources Regulatory compliance (MAR, MAD, MiFID II, Dodd-Frank) Code quality, version control, and best practices. Soft Skills: Strong storytelling and communication for technical and non-technical audiences Collaboration with consultants, MAR monitoring teams, and technology stakeholders Stakeholder management and requirements gathering Leadership, mentoring, and team guidance Problem-solving and critical thinking Adaptability and continuous learning Nice to have Understanding of Financial Markets Asset Classes (FX, FI, Equities, Rates, Commodities & Credit), various trade types (OTC, exchange traded, Spot, Forward, Swap, Options) and related systems is a plus Surveillance domain knowledge, regulations (MAR, MIFID, CAT, Dodd Frank) and related Systems knowledge is certainly a plus Other Languages English: C2 Proficient Seniority Senior