About

I spent fifteen years preparing to become an orthopaedic surgeon. When it came time to enter the Match, I chose not to.

From the outside, that looked like a break with everything that came before. Looking back, it was the same decision I had been making since childhood: find where I could be most useful, learn the material, and build what the work required.

To understand that, you have to start on a cattle farm in rural Ohio.

From a young age, my deepest desire was to be a force of good in the world.

Growing up on a cattle farm taught me what that meant in practice. There were animals to feed, crops to cultivate, machinery to operate and repair, timber to work, and neighbors who showed up when something broke or someone needed help.

I learned early that doing good meant being useful: notice what needs attention, use the means available to solve the problem, and stay until the job is done. Care was concrete.

Growing up around my mother’s work as a nurse practitioner gave that desire a direction. Medicine looked like a place where practical skill and love for people could meet. It offered a way to make a real, direct difference in another person’s life.

If I wanted to be a force of good, becoming a doctor seemed like the clearest way to do it. I decided early that medicine would be my path.

Between the farm and college, I spent two years as a missionary in South Korea. My faith gave service a deeper meaning, and Seoul widened my sense of who I was responsible to. I learned Korean well enough to teach and listen, adapted to a world far from the one I knew, and came home with an enduring affection for Korean people, culture, and—of course—kimchi.

After missionary service, I began my journey toward medicine at Brigham Young University, where I also walked on to the rugby team. I had the pleasure of playing in a high-performance environment where we trained hard and routinely competed against some of the best teams in the country.

Rugby taught me to trust people under pressure. It turned force, structure, timing, and judgment into something a team had to feel together. By the time I was thinking seriously about medicine, I already knew that I was drawn to high-performance environments that demanded skill, teamwork, and all-in dedication.

Medical school came next, and I quickly knew which specialty interested me.

Orthopaedic surgery felt like the natural place for my interests, aptitudes, and background to converge. I enjoyed the high-performance environment. Years of athletics had given me an intuitive understanding of musculoskeletal injuries. A blue-collar upbringing spent around machinery and power tools made surgical instruments feel familiar in my hands.

Orthopaedics was medicine with its mechanics exposed: structure, load, alignment, motion, failure, and repair. The work asked a question I had been asking in different forms since childhood: what is broken, what forces caused it, and how do we put it back together?

My blue-collar background soon proved valuable for another reason.

Shortly after beginning medical school, a pet of mine needed life-saving surgery that I could not afford. I put the bill on a credit card and started a business making and selling hardwood furniture to pay it off.

What began out of necessity started to grow. After several months and a great deal of black walnut, my one-man garage operation had become an industrial-grade workshop filled with jigs, dust collection, and heavy machinery. Before long, I was managing websites, shipping furniture, refining processes, and hiring employees.

I enjoyed the satisfaction of making physical things that brought other people joy. But I also discovered that I loved building the enterprise around the work: finding customers, solving bottlenecks, designing systems, and bringing together the pieces required for an organization to function.

When something important was out of reach, my instinct was not to wait for permission. It was to build a way to reach it.

The business was fun, and building it felt unexpectedly natural. But I was not yet sure what that meant for my medical career.

Those same years, I spent two summers treating patients and assisting in surgeries in Eswatini and the Himalayas.

Access to care stopped being an abstraction. It became particular people—people who needed skill, tools, and cures no less than anyone near a major medical center, but who happened to live far from the systems where medicine concentrates its most advanced capabilities.

I still wanted to care for patients like them. But I began to question how I could continue helping people in far-off locations as an orthopaedic surgeon. My knowledge and hands could only serve the patient I could physically reach. Geography determined who had access to expertise.

Again, I did not yet know what this would mean for my future. But the problem of reach stayed with me.

Late in medical school, a research project handed me a repetitive task: assigning the same measurements to thousands of X-rays.

The repetition itself felt like evidence of a missing tool. If a trained person could look at image after image and make the same kind of judgment, perhaps a model could learn the pattern. I taught myself enough computer vision to build my first machine-learning system: a program for reading those X-rays.

What began as a way to remove repetitive work became a different conception of a medical instrument. A scalpel extends the hand. A model can extend judgment. Software could learn from medical data, repeat careful reasoning, and travel beyond the room where it was created.

I took a clinical-AI position at Harvard Medical School and taught myself to code well enough to work alongside the engineers around me. About six months into that year, ChatGPT launched.

I had already been moving toward machine learning. The launch did not create the interest, but it changed my sense of the timeline. The honest question was no longer only what AI could do then. It was what might become possible over the same thirty years that would have been my surgical career.

The patients I had met in Eswatini and the Himalayas gave that possibility moral weight. An intelligent system did not have to live in Boston, San Francisco, or an advanced hospital. Biomedical knowledge could become available wherever a question was asked—even in places a specialist might never reach.

That became the argument of my TEDx talk, Doctors Who Code: the people who understand disease most closely should help build the intelligence meant to treat it, because that intelligence can travel farther than any individual physician.

Software was the first instrument I had encountered that could carry trained judgment without carrying the person.

Even then, I was still interviewing for orthopaedic residency. Surgery was not a backup plan. It was the path I had built my life around, and I loved much of what the work demanded.

But the choice had changed. It was no longer medicine or technology. It was which instrument could carry the obligation farther.

When the Match came, I chose not to submit my name. I went to Carnegie Mellon to become technical enough to build what I believed medicine would need.

I did not want to remain only a medical person advising technical people. If I was serious about using computation to work on disease at scale, I needed to understand the substrate myself.

Carnegie Mellon became an apprenticeship in computing from first principles. I went there to learn how software, algorithms, models, and systems actually work—not merely how to apply tools that other people had built.

It was not a detour from medicine. It was preparation to build systems medicine did not yet have.

The deeper I went, the more I was drawn upstream.

Clinical AI often begins after disease has already made itself visible: an image to interpret, a diagnosis to classify, or a treatment decision to support. But the most consequential questions begin earlier. What is happening inside the biological system? What change would alter its trajectory? Which intervention is worth testing before years of expensive physical experimentation begin?

That is what drew me to the virtual cell problem.

A virtual cell is a model of cellular behavior that can be queried and perturbed: change a gene, introduce an intervention, and reason about how the system may respond. It is a form of biomedical intelligence—one that can help people understand living systems and decide what biological change to pursue next.

Because it is computational, that intelligence does not have to remain concentrated in a particular laboratory, hospital, or geography. It can become available to anyone, anytime, anywhere.

The problem brought every part of my path together: medicine, biology, physical intuition, machine learning, first-principles computing, company building, and the conviction that advanced biomedical knowledge should not depend on proximity.

Galen is the company I am building to pursue it.

Now I am in San Francisco building Galen, the virtual cell company. We build models that help biology teams decide what change to pursue next: making cellular behavior more legible, comparing interventions before expensive work begins, and grounding computational claims in experiment.

The farm taught me that doing good meant being useful and that care was something you practiced with your hands. Faith widened the circle of people I felt responsible to. Rugby and surgery taught me to trust skilled teams under pressure. The workshop revealed that I loved building not only objects, but enterprises. Patients far from advanced medical systems taught me that expertise trapped by geography was not enough. Machine learning showed me that intelligence could travel. Carnegie Mellon gave me the technical foundation to build it myself.

Galen is where those lessons converge.

I do not intend to spend my life only treating disease after it appears. I intend to help build intelligence capable of understanding biology deeply enough to change what is possible—to make disease more predictable, interventions more deliberate, and biomedical knowledge available wherever it is needed.

The greatest advances in human health during our lifetime will emerge from the convergence of biology and information. When they do, the most powerful medical instrument may not be confined to an operating room or a laboratory. It may be a model accessible from any code terminal, anywhere in the world.

I did not leave medicine. I followed its purpose upstream—from repairing the body, to understanding the cell, to building biomedical intelligence that can help anyone, anywhere.