Portfolio
Selected AI & Quantitative projects in previous roles
AI-Powered Quantamental Analytical Platform
Core Components
Agentic Rebalancing & Quantamental Analysis →
Architected quantamental trading agents powered by leading LLMs including Qwen 3 Max, DeepSeek 3.2-chat, and GPT-5.1 to automate portfolio rebalancing and optimization. Built an end-to-end quantamental pipeline using embeddings, vector search, and real-time web retrieval for macro, fundamentals, and sentiment signals. Integrated execution via the Alpaca API and incorporated prediction market data for forward-looking market expectations.
Hedging Derivative Strategy Generation with Fine-tuned Models →
Developed fine-tuned models using historical option data for hedging derivative strategy generation. Applied SFT and RL methods to train models on options pricing, Greeks calculation (delta, gamma, vega, theta), volatility surface modeling, and hedging optimization. Built market risk infrastructure supporting VaR calculations, stress testing, and factor exposure monitoring. Integrated with Thinking Machine Tinker API for advanced reasoning in complex derivative scenarios.
Active Portfolio Management & Alpha Research
Apply statistical and machine learning techniques (XGBoost, neural networks) to uncover patterns in market behavior and build predictive models for alpha generation. Implement systematic portfolio construction and optimization using Python (scikit-learn), including dynamic position sizing, sector rotation, and feature engineering from alternative data sources. Design data-driven experiments and A/B testing frameworks to validate hypotheses and continuously refine allocation weights for risk-adjusted returns.
Previous Experience
MLOps Platform & Federated Learning SDK
- Collaborated with ML researchers and engineers to productionize FedML Federate—a zero-code, cross-platform federated learning SDK deployable on edge GPUs, smartphones, and IoT devices.
- Drove product roadmap for TensorOpera Deploy (model serving), GPU cloud pricing, and monitoring infrastructure from 0-1 at $19.5M funded startup.
- Translated cutting-edge research into user-facing MLOps tools, bridging the gap between research prototypes and production-grade deployments.
ML Platform & Privacy Computing
- Designed EAS (Elastic Algorithm Service) deployment module with blue-green release and pricing features, enabling ML model deployment as inference services with auto-scaling, canary releases, and real-time monitoring.
- Led federated learning privacy computing module design and national security compliance assessment.
CV Defect Detection Engineering
- Collaborated with CV researchers to productionize defect detection models for ultra-small precision instrument quality inspection.
- Built data pipelines for batch processing and edge annotation of thousands of multi-angle instrument images.
- Tranformed research prototypes & models into production-grade deployments and benchmarked detection accuracy.
Research Interests
Exploring the intersection of AI/ML and quantitative finance with focus on systematic trading strategies. Current research areas include agentic AI systems for trading automation, LLM applications in financial research, statistical and machine learning techniques for alpha generation, options market microstructure and volatility modeling, and portfolio optimization under various market regimes.