Hire Jack G. - AI Engineer - New York

Building custom agent harnesses from scratch to deploy coding-style agents on long-horizon, multi-step tasks across the healthcare revenue cycle. Developing internal evaluation harness to stress-test agent reasoning, creating data flywheels required to fine-tune models directly against the harness's constraints. Engineering robust, skill-based tool-use (including MCP) that enables agents to reliably navigate, parse, and reason over highly complex, unstructured clinical documents and guidelines.

* Postdoctoral Research Fellow at Mass General Brigham and Harvard Medical School * Advancing AI alignment in healthcare through: * Evaluating how medical knowledge is encoded in large language models * Developing robust frameworks for evaluating AI systems in diverse clinical scenarios * Creating new benchmarks for medical AI transportability and generalization

As a postdoctoral researcher at MIT's Laboratory for Computational Physiology under the guidance of Dr. Leo Celi, my work focuses on the intersection of causality, explainability, and interpretability in healthcare AI. I am deeply involved in developing and refining models that not only make accurate predictions but also offer actionable insights into health equity and bias. The overarching goal of our research is to create data-driven solutions that are both technically sound and ethically responsible, aiming to narrow health disparities and improve patient outcomes across diverse populations.