I'm a Founding Engineer at Weco AI, building self-improving AI agents for engineers and scientists (such as AIDE [1, 2]). I led the development of AIDE² [3], the first evidence of recursive self-improvement on AI R&D tasks (blog, tweet). My work has been used by both industry (OpenAI [4, 5, 6, 7], Meta [8, 9], Google [10], Microsoft [11], Amazon [12], Sakana AI [13, 14], METR [15, 16], UK AI Security Institute [17]) and academia (CMU [18, 19], Stanford [20], UC Berkeley [21]).

Prior to this, I was a researcher at the Robotics Institute at Carnegie Mellon University working on large multimodal models, robotics and time-series for healthcare (such as AutonFeat, BIFURC). I also spent time at TTIC working with Matthew Turk and UChicago Booth working with Sendhil Mullainathan on fairness and alignment for vision models (such as ASAC Guided Curriculum Learning).

I enjoy building high-performance implementations of my work and applying AI to healthcare, climate, scientific problems. Outside of research, I enjoy spending time outdoors hiking, surfing, and playing golf.

• AIDE²: Recursive Self-Improvement of AI Research Agents [paper] [blog] [tweet]
• AIDE: AI-Driven Exploration in the Space of Code [code] [readme] [project] [paper]
• Utilizing Adversarial Examples for Bias Mitigation and Accuracy Enhancement [paper]
• AutonFeat: A high-performance Python package for automatic and distributed time series feature extraction and selection [code] [readme] [docs]
• tsfresh: A time series feature extraction package [code] [readme] [docs]
• Denoising Diffusion Probabilistic Models (DDPMs) [code] [paper]
• Resource-conscious high-performance models for 2D-to-3D single-view reconstruction [code] [readme] [paper]
• pynn (Deep Learning Framework with pure NumPy Computation) [code] [readme] [demo]
• VanillaGAN (Vanilla GAN experimentation library) [code] [readme]
• ConditionalGAN (Conditional GAN experimentation library) [code] [readme]
• DCGAN (DC GAN experimentation library) [code] [readme]
• PSNRGAN (Contrastive PSNR GAN experimentation library) [code] [readme]
• Monocular Depth Estimation [code]
• Neural Artistic Recreation (A CLI for Neural Style Transfer) [code] [readme] [demo]

• Bifurcation identification for ultrasound-driven robotic cannulation (Oral) [paper]

• HuggingFace Text Generation Inference [code] [readme] [docs]
• CUDANN (Distributed Deep Learning Framework accelerated on NVIDIA GPUs) [code] [readme]
• FastConv (Multithreaded GPU CUDA kernels for Convolution) [code]
• Ray Tracing (using Monte-Carlo Algorithm on GPU Accelerators) [code] [readme]
• Advection Diffusion Simulation (Multithreaded, Shared Memory Parallelism, Distributed Memory Parallelism) [code] [readme]
• N Body Particle Simulation (Multithreaded, Shared Memory Parallelism, Distributed Memory Parallelism) [code] [readme]
• Distributed Poisson Solver (using Conjugate Gradient Optimization) [code] [readme]
• Image Editor via Convolutions (using Work Stealing and Work Balancing parallel schemes) [code] [readme]
• Sparse Linear Solver (using the Map Reduce parallelism scheme with Conjugate Gradient Optimization) [code] [readme]
• Image Editor via Convolutions (using Pipeline and BSP parallel schemes) [code] [readme]
• Twitter Application (using Producer-Consumer parallelism model) [code] [readme]

• Boosting and Boostability (An understanding through Computational Learning Theory) [code] [paper]
• Financial Forecasting of TSLA (using sentiment analysis, feature engineering, and RNNs) [code] [readme] [report]

• GoLLUM - A GoLang Compiler [code] [readme] [docs]
• Unix Shell [code] [readme]

• Climbing Mount Everest (A text-based adventure game) [code] [readme]