Agents · Trustworthy AI · New York

Building agents worth trusting, and the worlds that teach them.

I'm joining the AI Hub at BNY to work on agentic software engineering and trustworthy AI systems. My research centers on long-horizon agents, continual learning, scalable RL environment creation, evals, alignment, and other frontier directions toward AGI and ASI. Before this, I was a data scientist in Neuroscience at Mount Sinai, building ML for electrophysiology, molecular neurobiology, and animal behavior, and foundation models for genomic DNA sequences.

Read about my research Download CV

01Research focus

Research
A

Long-horizon agents

Agents that carry work through over long horizons and keep learning as they go: continual learning, memory, and adaptation without forgetting.

B

Scalable RL environments

Creating training environments for agents at scale: diverse, verifiable, and open-ended, plus semi-verifiable domains and the algorithms that learn from them.

C

Benchmarks & evals

Measuring what agents can actually do, with evaluations that hold up over long horizons and resist saturation.

D

Trustworthy AI

Making agent behavior reliable, legible, and safe to deploy where the stakes are high.

E

Alignment & governance

Keeping capable systems aligned with what people intend, and the policy and institutions to govern them.

F

Frontier directions

Research paths toward AGI and ASI, and what it takes to get there well.

02Also exploring

Secondary interests

AI & AGI

  • Meta-RL and open-ended adaptation

    Agents that make sense of loosely specified environments, work out what they need to learn, and ask questions when they should.

Biology & neuroengineering

  • Regenerative biology, especially neural regeneration
  • BCI and neuromechatronics
  • Synthetic and engineering biology

Philosophy

  • Philosophy of AI, engineering, and neuroscience
  • Computational methods in philosophy
  • Philosophy of physics, computational metaphysics, and more speculative approaches
  • Aristotle and Olaf Stapledon

03Selected projects

All projects
P/01

AI-Neuroscientist

An autonomous research agent that plans and executes bioinformatics analyses on spatial and single-cell transcriptomics data, writing and running its own notebook code against a live kernel.

  • LLM
  • agent
  • bioinformatics
  • single-cell
P/02

AlphaGEmmaNOME

A Gemma-powered genomic copilot that calls AlphaGenome, renders epigenomic tracks, designs genome edits, and fine-tunes the agent locally.

  • genomics
  • LLM
  • agent
  • AlphaGenome
P/03

SAM3-WebTracker

A full-stack web app for interactive video instance segmentation and tracking on Meta's SAM 3, with a downstream pipeline for quantifying animal behavior from tracked masks.

  • computer-vision
  • SAM3
  • video-segmentation
  • object-tracking
P/04

Dynamic Missingness-Aware Meta-Ensembling

Ensemble statistical learning algorithms for dealing with large amounts of missing data.

  • machine-learning
  • missing-data

04Recent publications

All publications

05About

Background

Most recently I was a data scientist in the Neuroscience Department at the Icahn School of Medicine at Mount Sinai, where I worked on machine learning, AI, and high-performance scientific computing for electrophysiology, molecular neurobiology, and animal behavior quantification, and built foundation models for genomic DNA sequences.

Before that, I was a master’s student in the CUNY Graduate Center’s Department of Computer Science, where I worked as a graduate research assistant in the Hunter College Distributed AI Lab, under the supervision of Professor Anita Raja. I developed machine learning and data mining methods for clinical applications, with a focus on AI for sequential decision-making and machine learning tasks involving large amounts of missing data.

During my time at CUNY, I also worked as a research data scientist intern at the Janssen Pharmaceutical Companies of Johnson & Johnson, where I developed machine learning and signal processing pipelines to identify digital biomarkers of sleep and activity in immunological disease populations via wearable activity monitors.

As an undergraduate at Stony Brook University, I majored in applied math & statistics and philosophy, with research focuses on formal methods in metaphilosophy, philosophy of physics, and mathematical logic. My undergraduate research in philosophy was supervised by Professor Gary Mar.

I also write on Substack at Future and Ever.

Personal

I am married to my wife, Amy, who is a breathtakingly-talented fine artist. Check out her work on her portfolio site and Instagram.

Outside of computer science / engineering, I like to run long distances, read literature, sci-fi, and psychological thrillers, and attempt to stay up-to-date with a few branches of contemporary metaphilosophy and philosophy of mind.