Portfolio

Experimental Projects

Selected case studies across AI, ESG analytics, enterprise systems, and experimental work.

Experimental
RL-Driven Portfolio Rebalancer

Reinforcement-learning agent that learns to rebalance a multi-asset portfolio under transaction-cost and risk constraints.
- Python
- PyTorch
- Stable-Baselines3
- Pandas
Experimental
LLM Research Assistant for Podcast Production

Custom research-assistant agent that prepares podcast episode briefs from a topic + guest list.
- TypeScript
- Anthropic SDK
- SerpAPI
- Notion API
Experimental
Edge Inference Benchmark Harness

Reproducible benchmark suite comparing on-device LLM inference across consumer hardware configurations.
- Rust
- Python
- llama.cpp
- ONNX Runtime