In this interview, Angelia Yang talks with Jorge Colindres, co‑founder of Radical.ai, about his journey from academic frustration to building a company that uses AI‑driven agents to discover and sell novel materials. Colindres explains how he grew disillusioned with the shallow applications of machine learning he saw in startups—calendar optimization, email copy—despite believing the technology was transformative. He read over 200 research papers to verify the power of ML and concluded that the field deserved more ambitious, high‑impact problems. Together with his co‑founder Joseph, they settled on materials science as a domain where AI could make a breakthrough, noting that legacy giants like Dow, DuPont, 3M, and BASF are risk‑averse and slow to innovate. Radical.ai’s business model is to create a new operating model for science and sell the resulting materials, not just predictive models. Their approach uses autonomous ML agents that generate hypotheses about material properties (hardness, thermodynamic stability, oxidation resistance), design experiments, and close a rapid feedback loop by iterating on experimental results. The conversation highlights the founder’s vulnerability, the drive to tackle grand challenges, and the technical‑business strategy of leveraging AI for material discovery.
Have you ever felt truly vulnerable as a founder?
Every day. Trying to go after a problem as big as the one that Radical.ai is pursuing is one of the most painful endeavors I have ever undertaken. I became frustrated because I believed that machine learning was this incredibly powerful technology. Yet I kept seeing companies doing calendar optimization or better email copy. And I went down the rabbit hole and I started reading research papers, probably read north of 200 research papers because I wanted to get to a root. I turned to my co-founder Joseph, who happened to sit next to me, and then said, Why are we not solving cancer with machine learning? I was starting to invest in a lot of machine learning companies, and I actually became frustrated. I became frustrated because I believed at a very deep level that machine learning was this incredibly powerful technology that was going to change the world. And yet I kept seeing companies that I did not think were actually going after the biggest, hardest of problems, right? These were companies that were doing calendar optimization or better email copy, all things that are quite useful and we use them all today. And I like having those, don't get me wrong, but they were not in the same vein as what we were hearing in terms of the magnitude of impact that AI could have. And I really wanted to get to the root of it. I wanted to understand, am I wrong? Is the technology actually not that impressive? Or— and so I went down the rabbit hole and I started reading research papers, research paper after research paper. I probably read north of 200 research papers and I concluded that that yes, the technology is incredibly powerful. It had so much promise for humanity. And then it was immediately that I thought, okay, well then we have to create companies that are actually leveraging it to its fullest. And it was at that moment that I turned to my co-founder, Joseph, who happened to sit next to me, and I started talking to him about what I was thinking. What I turned to him and said is, why are we not solving cancer with machine learning? And he said, well, I don't know about cancer, but let's look into the different spaces. And material science was one that was a natural fit.
At the end of the day, what are you selling?
We sell materials. What we try to do as a business is not only create a new operating model for science, but really to create a new materials company. If you look at all of the big materials companies that are out there, whether it's Dow, DuPont, 3M, BASF, all of these have been around for 100, 150 years. They all make billions of dollars in revenue. And so they're not really incentivized to go after the next generation of materials challenges. They're not incentivized to take risks. They're not incentivized to try to create new novel discoveries that might unlock the future for humans.
So it's not just predictive modeling, trying to predict some material, whether let's say it's stable or not stable. I'm making— I'm not a material scientist. I'm just making things up. And then you go back to the agents and then try to design, like, let's try to make it and then see if it satisfy your criteria, then you can go back, send that feedback loop back.
What the agent will do is it will, it will say, I'm going to try to create a material that has these conditions, these properties. It will be hardness of this measurement. It will be, have a thermodynamic property or oxidation resistance of this level. And then it will use all of the tools that are available in order to craft that hypothesis, including understanding whether or not the at the structural level, this is a stable material. So all of that, like you said, is a part of the process.
Is this the fastest possible feedback loop that you're creating?
Yes, this is by far the fastest possible feedback loop for material science, and we believe it is the archetype for how science should be done as a whole. Today, science is a very manual iterative process. A human scientist comes up with a hypothesis. They, uh, ultimately design an experiment that they go run in the lab. They wait a few weeks for results. They publish a paper and they repeat that cycle over and over again. In that process, there is tons of valuable information that gets lost. For example, when we publish a paper, we publish on what worked despite the fact that there are 90, 95% of iterations that did not work. We just don't talk about those in the paper. It's, it's one of the most important things that you could capture as a scientist. Again, so much of what we do in the lab is through iteration, is through the failures that we learn how to eventually come up with good experiment. And so you need to be able to capture those things because those are the things that help you directionally get to where you want to go. As an engineer here at Radical, you will weekly see physical embodiments of that mission coming to life. A couple weeks ago, we did a torch test on one of our materials, which is a third-party test to understand, you know, can our material survive under extreme temperature, so 3,000 degrees. And in that test, we discovered that our materials are actually outperforming industry standard materials that have been around since the '60s. And so that's an early test. There's a lot more to do beyond that, but it does act as a sign that, hey, this works. What we are doing can actually change how things happen.
