Applied AI and Physics, Research and Engineering
I enjoy the intersection of AI, physics, and engineering. I've worked across agents, robotics, simulation, machine learning, and physical modeling, and I'm especially drawn to emerging problems where scientific ideas can lead to practical results.
These are some of the projects I work on in public, from local agents and full-precision inference on small GPUs to simulation environments where agents learn from physical outcomes. I hope they are useful to you in one way or another.
Agent systems
A policy-protected local agent that keeps working toward the task.
Talk to it from the web, Telegram, or WhatsApp, and approve important actions before they run.
Inference systems
Run large, full-precision models on smaller GPUs.
It ran a 29.5 GB model on an 8 GB GPU by streaming losslessly compressed weights one layer at a time.
Local AI
A complete local model deployment and benchmarking suite.
It checks your hardware, estimates which models fit, and measures the speed, quality, and memory you actually get.
CITY_PULSE / SCORE 100%Agent evaluation
Bring AI agents and physics into the same experiment.
An agent builds something in a simulated world, sees what happened, and gets another chance to improve it.
Robotics
Design, evolve, and test robots in a reproducible physics lab.
Edit a robot body, run it in physics, and trace a failure to the body, controller, task, or simulator.
Computer vision
Train, compare, and run semantic segmentation from one platform.
One setup trains a segmentation model, compares it, and runs it on images or videos.
Notes on LLM inference, memory use, and performance.
LLM inference
Speculative decoding
AI Lead, Language Modeling Engineering
I lead NLP and language-model engineering in Oxy's Applied AI Center of Excellence.
AI Lead
I was responsible for 19 models from problem definition through deployment, spanning machine learning, NLP, and optimization.
Associate Editor
I served for more than 10 years as an Associate Editor, overseeing peer review and editorial decisions for more than 250 scientific manuscripts.
Senior Research Specialist
I published 4 internal technical papers on signal processing, data-driven modeling, and decision-making. I also led the assessment and integration of Boston Dynamics Spot and other quadruped robotic platforms.
Data Scientist / Robotics Software Engineer
I developed a custom SLAM and sensor-fusion method for an omnidirectional mobile robot, using motor effort and onboard sensing to estimate and correct motion drift for better pose estimation.
PhD, Dynamic Systems and Control · Portfolio in Applied Statistical Modeling
My doctoral research focused on hybrid modeling: combining AI and physics to improve prediction and control in physical systems. Doctoral dissertation SciPy paper
Data Scientist / Software Engineer
I worked across the full software and data-science lifecycle of ABBL, from pattern-recognition models through product development and commercialization. The automated directional-drilling adviser was tested across more than 250 wells. ABBL service
MSc, Petroleum Engineering
My MSc research combined experiments and numerical methods for non-Newtonian flow and freely rotating drillstrings. I later collaborated on work pairing a deep-learning model with genetic-algorithm optimization. Request master's thesis Genetic-algorithm paper
BSc, Petroleum and Natural Gas Engineering
I built my engineering foundation in transport phenomena, numerical methods, and subsurface systems.
JNGSE
Energies
Energies
Eight selected grants
Lead inventor
Lead inventor
Lead inventor
Lead inventor
Co-inventor
Co-inventor
Co-inventor
Co-inventor
I am easiest to reach on LinkedIn. I am always glad to hear from people working on agents, local AI, simulation, or AI for physical systems.
Connect on LinkedIn
