Designs and implements systematic trading platform in US equity markets that integrate real-time intelligence into optimized trading strategies. Creates models and optimization engines driving equity trading algorithms — VWAP, LSA, IS, and Dark — to improve execution quality and scale of deployment given varying client objectives. Creates analytical insights based on historical data using Python and KDB/Q, and determines optimization strategies that improve implementation short falls and liquidity capture of trading algorithms. Develops analytical systems to produce real-time insights and mitigate risk based on data in Amazon Web Services (AWS) services and streaming data in Kafka. Designs A/B test aiming to gain market insights and drive optimization. Conducts performance reviews, continually validates models in production, examines A/B test results, and proposes new strategies to improve performance of algorithms. Collaborates with product team to create product roadmap, develop quantitative requirements to production systems, create prototypes to drive innovation, and grow technology team with competency to drive speed of implementation.
Primary Responsibilities:
• Establishes performance benchmarks and analytics to evaluate systematic trading platforms.
• Proposes models and logics to improve trading algorithms by decomposing performance indicators and examining system logs.
• Conducts transaction cost analysis and continuous evaluation of client orders.
• Applies statistics and machine learning techniques to create liquidity, price and performance prediction in trading applications.
• Integrates in agile squad to propose, implement and test quantitative solutions in production systems.
• Works side-by-side with client facing team to create trading solutions for clients.
• Establishes thought leadership via market microstructure structure and systematic trading research.
• Works closely with product developers, traders, clients, and software developers to deploy electronic trading products.
• Researches and designs trading systems, including algorithmic optimal trading strategies, order placement strategies, smart order routing, and portfolio trading.
• Optimizes model parameter selection by using both real-world trading data and simulated environments to improve performance of the trading strategies.
• Develops and implements advanced simulation techniques to model dependencies between financial instruments, improve accuracy in simulations, and reduce variance.
• Collaborates with client-facing teams to create trading solutions for clients. Creates tools, prototypes, and simulation engines to streamline processes and test new ideas.
• Builds and deploys machine learning models for price, liquidity and performance prediction in trading applications.
• Conducts market structure studies and provides valuable market insights to businesses.
• Participates in creation of next generation brokerage products.
Education and Experience:
Bachelor’s degree (or foreign education equivalent) in Computational Finance, Financial Engineering, Financial Mathematics, Data Science, or a closely related field and six (6) years of experience as a Director, Financial Engineering (or closely related occupation) performing transaction cost analysis in US markets and analyzing historical trading data using KDB/Q or Python.
Or, alternatively, Master’s degree (or foreign education equivalent) in Computational Finance, Financial Engineering, Financial Mathematics, Data Science, or a closely related field and two (2) years of experience as a Director, Financial Engineering (or closely related occupation) performing transaction cost analysis in US markets and analyzing historical trading data using KDB/Q or Python.
Skills and Knowledge:
Candidate must also possess:
• Demonstrated Expertise (“DE”) designing and implementing logics to improve systematic trading algorithms (VWAP, POV, Dark, LSA, or IS), examining raw logs and conduct transaction cost analysis using Python or KDB/Q; deploying systematic trading systems and logic within Amazon Web Services (AWS), streaming data in Kafka, and signal stream-processing in Flink.
• DE developing, analyzing, and evaluation machine learning algorithms, volatility forecasting, volume profile generation, and liquidity signals using Python, R, hmmlearn, or Pytorch.
• DE creating simulation engines using Aliasing Algorithm, Antithetic Variables, and Stratification; and designing programs to reflect real-world price dynamics and market microstructures (structure of exchanges and trading venues, price discovery process, determinants of spreads and quotes, intraday trading behavior, and transaction costs) using KDB/Q or Python.
• DE solving financial market allocation issues using Linear Programming, Quadratic Programming, Stochastic Optimization, and CVXPY (a Python package for convex programming).