About the Role
Our client is seeking a senior Quantitative Researcher to join their Delta One desk.
You will focus on the hedging strategies. We are looking for a researcher who can apply machine learning and rigorous statistical analysis to optimise inventory holding, signal generation, and portfolio construction.
Key Responsibilities
Inventory Optimization: Apply machine learning techniques to model inventory dynamics, predict availability, and optimize the costs associated with holding positions.
Signal Research: Research and backtest signals related to supply/demand imbalances and flow dynamics to improve inventory turnover and yield.
Portfolio Construction: Determining the optimal value of a basket based on hedging costs and strategy rather than theoretical models.
Systematic Hedging: Design and simulate hedging strategies for linear (Delta One) portfolios.
Model Deployment: Implement your models and logic into the production environment using Python.
What We Are Looking For
Experience: 5+ years of experience in Quantitative Research, Inventory Management, or Systematic Strats.
Domain Knowledge:
Strong understanding of Inventory Management and Hedging mechanics.
Expertise in Portfolio Optimization and Signal Research.
Explicit Note: No stochastic calculus, exotics pricing, or non-linear derivatives background required.
Technical Skills:
Quant First: While Python is required for implementation, the priority is your ability to apply mathematical and statistical concepts (Machine Learning, Optimization) to financial problems.
Proven experience deploying Machine Learning models (e.g., for signal generation or inventory prediction) in a live environment.
Education: Advanced degree (Masters/PhD) in a quantitative field.
If this outstanding opportunity sounds like your next career move, please submit through "Apply Now" or send your resume in Word format to Charlie Kim at resume@pinpointasia.com and put Quantitative Researcher – (Delta One) - J12433 in the subject header.
Data provided is for recruitment purposes only.