Agents, models, and systems I built.

A domain-agnostic MARL framework for evaluating trained policies under heterogeneous event-driven execution and realistic observability constraints

A configurable LLM benchmarking template for repeatable model, prompt, dataset, and metric validation

A Deep Learning framework with customized GPU and CPU backend in C++ and Python

A private, configurable AI resume assistant with LangChain agents, CV rendering, and a full-stack review workflow

A lightweight local inference-serving toolkit for registering models and exposing prediction endpoints quickly

Researched and developed a classifier-free guidance-based latent diffusion model for autonomous vehicle motion forecasting using UNet and Transformer as backbones