The AI behind Formula One race-day decisions
The AI behind Formula One race-day decisions
Formula One elevates its drivers to the status of swashbuckling global celebrities. But behind them is a data-driven operation looking to find the slightest edge over their rivals. Signal talks to Joey McMillan, lead race strategist for the Mercedes-AMG PETRONAS F1 Team, about one of the most enigmatic roles in the sport, the team’s new partnership with Microsoft and embracing the power of AISunday, May 3, 2026, Miami International Autodrome, Miami
Joseph “Joey” McMillan has been watching the numbers, and the skies above. With the start of the Miami Grand Prix just a few moments away, the Lead Race Strategist for the Mercedes-AMG PETRONAS F1 Team sits at his console, perched on the pit wall above the start line, listening to multiple different intercom channels at the same time, checking the weather reports and thinking about the race ahead.
The team’s drivers have performed well over the race weekend, both in practice and in qualifying. British driver George Russell is starting fifth on the grid but, ahead of him, Kimi Antonelli is in pole position. The Italian teenager has been the breakout star of the season so far and is aiming to win his third Grand Prix in a row. At 19, Antonelli would be the youngest driver ever to achieve that feat.
Antonelli and Russell are just two of Mercedes’ vast F1 team, around 1,300-strong, mainly engineers dedicated to making their cars go faster. But McMillan isn’t an engineer. His job is not about squeezing an extra ounce of speed from the engine, but saving time by executing a plan of action on the track, analyzing the variables his drivers can’t see and can’t control. “The strategist is sort of the black sheep in the sense that we are not really focused on making the car [go] faster,” explains McMillan. “Our job is to try and navigate those two cars through the race weekend. And to do that, we’re often looking at a lot more than just our car. We’re focused on every car on the grid, what every team is doing.”
Like all sports, F1 is obsessed with marginal gains and McMillan’s mission is to find an edge on rival teams, making decisions based on multiple streams of data and running multiple simulations. In a sport where a thousandth of a second can be the difference between winning and losing, every factor needs to be considered. “By far the most important thing we do is decide what tire compounds to use in the race and what laps to make pit stops on,” he says. “That combination is known as the strategy.” There are five types of tires to choose from during a race, all color coded for different conditions: three types of slicks for dry conditions (soft, medium and hard), and two treaded tires (intermediates for light showers and wet tires for heavy rain). “If we knew the degradation rate of each of those compounds, essentially how much slower they get each lap in milliseconds, strategy would be so easy.”
But things are rarely easy in F1. As well as monitoring the pace of rival cars and trying to judge how the tarmac will affect the tires, the strategy team’s simulations also need to know the answer to the question dominating McMillan’s thoughts as he sits at his trackside console. Is it going to rain? And in Miami, a storm is coming. The race is taking place at the start of May, six weeks before Florida’s Atlantic hurricane season usually begins, but the bad weather is ahead of schedule. The threat of lightning strikes is so severe that the organizers have brought the start of the race forward by three hours.
Rain briefly fell in the morning, and McMillan is being fed local weather radar data that suggests rain might fall again during the race. Will it be a passing shower? Or a deluge? A decision has to be made about which tires to start on: the faster slicks, the intermediates or the wet tires. That choice could win or lose the race before it even starts.
McMillan and the team make a play based on the data at hand and their instincts. The drivers will not start on wet tires, they will be on slicks and hope the weather holds. As the lights go out and the race begins, the drivers roar toward the first corner on a dry track under skies pregnant with rain. And then all hell breaks loose.
Rudy Carezzevoli/Getty Images“When we run our simulations, we run an entire race. We want to run thousands, if not millions of these races. Now, with Azure Batch, we can”
McMillan has been a race strategist for a decade. The softly spoken Englishman was hired by the Mercedes F1 Team after finishing his mathematics PhD at Imperial College London. It was his first job after college and he’s been there ever since, moving up to Senior Race Strategist and, eventually, Lead Race Strategist. “We use about five or six strategists a weekend,” he says. “Out of those, maybe one or two of them will ever end up being the pit wall strategist who’s making the final decision, but you need a whole lot of people running models.”
Mathematics is only part of the job. What separates a good strategist from a great one is the ability to function under pressure. “It’s not super difficult in the sense that I don’t need high-level mathematics, nothing like the mathematics I was doing for my PhD,” says McMillan. “What makes a good general strategist? Someone who is a logical thinker, really good at modeling and data analysis. But what really makes you good at the pit job is to be able to make the decision in the moment, to do it very, very quickly, with very good communication skills… when you’ve got drivers, team principals, race engineers, lots of excitement and intensity. Once you realize you can do that, I think it’s pretty clear you’re going to be good at this.”
Machine learning, as McMillan calls it, has always been a huge part of his job – but in recent years, AI technology has greatly improved his ability to analyze more and more data at faster speeds. “My day-to-day, the actual Sunday doing the strategy, hasn’t changed a huge amount yet,” he says. So, what has changed? “I write quite a lot of code, but I’m really not a coder. I’m a mathematician, a statistician, a game theorist, but I’m not a coder. I understand what data we’ve got. I understand what I’d like to do with it. And [with] the advent of AI, like coding tools, I can do those things a huge amount quicker. I can now write models, write analysis, do things at a speed I could never dream of before.”
At the start of 2026, Microsoft signed a deal with the Mercedes-AMG PETRONAS F1 Team, a partnership that put Microsoft technology at the heart of its operation. After dominating Formula One for much of the 2010s, winning seven consecutive drivers’ championships between 2014 and 2020 and eight consecutive constructors’ championships between 2014 and 2021, the team was looking to build on that legacy. With a radically reengineered car performing strongly in testing, there was growing belief that 2026 could see the Mercedes-AMG PETRONAS F1 Team challenge for championships once again.
For the F1 strategy team, one of the biggest benefits of working with Microsoft is access to Azure’s vast cloud computing capacity. Using Azure Batch, they can run huge numbers of race simulations simultaneously, testing multiple scenarios before, and even during, a Grand Prix. “Azure Batch has revolutionized our race strategy – scaling thousands of simulations in real time, we can ramp up massive compute during the race so we get… insight when it matters most,” says McMillan. “When we run our simulations, we run an entire race. Every lap, every pit stop, every overtake, we’ve run the entire race beginning to end. We want to run thousands and thousands, if not millions, of these races. Now, with Azure Batch, we can.”
In the past, McMillan might run the simulations on a Saturday night while the team was at dinner, which could take up to an hour, sometimes more. Now those same simulations can take seconds and be run from the side of the track. “On a Sunday, in the race, we need those results back as fast as we can,” he says.
That data is then fed to the strategy team, who are updating their models live. According to McMillan, despite all the data that is now available to help make decisions, the only time you know for sure if you’ve made the right choice is at the checkered flag. “By the end of the race, you know the answer,” he says. All McMillan and the team can ask for is enough data to take as educated a guess as possible and make a successful final call. And in Miami, they do.
Toto Wolff (left) has been Team Principal at Mercedes-AMG PETRONAS since 2013. Photo credit: Sebastian Kawka“We’re often looking at a lot more than just our car. We’re focused on every car on the grid, what every team is doing”
As the drivers approach turn one of the Miami Grand Prix, the Mercedes of Kimi Antonelli is jockeying for position. To avoid contact with a rival car which has spun across the track, Antonelli briefly veers off himself. “It’s a brawl to open the Miami Grand Prix!” F1 TV commentator Alex Jacques shouts excitedly.
As Mike Tyson once famously said: “Everybody has a plan until they get punched in the mouth.” Following the chaos, Antonelli and his Mercedes are in second place and the race strategy McMillan and the team had planned for needs rethinking. The pressure is on McMillan and the whole operation to get Antonelli into the lead. He goes to his trackside console and assesses the data – from the other cars, from the weather forecasts and from Antonelli’s own telemetry readings. McMillan and the team have just moments to decide what to do next. “A huge amount of strategy is still experience and gut feeling,” he says.
He makes the final call. Antonelli will attempt an undercut. “An undercut,” McMillan explains, “is when you [pit] stop the lap before the car ahead of you. And because your tires are faster when they’re new, on that lap, where you’ve just made your pit stop and [the car you are trying to catch is] coming in to make their pit stop, you’re now quicker than them.” The hope is that you are fast enough to take the lead when your opponent is in the pits. In Miami, that strategy has a lot of moving parts. Antonelli has to first get to within one second of the leader. Then he has to pit at exactly the right time – one lap before them – while the pit team has to execute a perfect tire change. Finally, Antonelli will have to fly around the circuit on his new tires and make up the time so that he can emerge in first place.
And then, of course, there is the weather. It is raining at the time the undercut decision is taken, but McMillan has someone feeding him weather radar information live. She says it is not going to rain enough to go to intermediate tires for wetter weather. It would be catastrophic to make a pit stop for new tires designed for dry conditions and then the heavens open. McMillan concludes that his rivals are waiting for rain, so the team gambles and stays on soft tires. “But if you stop too early, you could be a sitting duck at the end of the race,” he says.
Joey McMillan, Lead Race Strategist, Mercedes-AMG PETRONAS F1 Team. Photo credit: Sam Bloxham“A huge amount of strategy is still experience and gut feeling”
At his console in Miami, McMillan is trying to filter the noise from his multiple different intercom channels. “You’ve got the driver channels, the engineer channels, strategy channels, aerodynamics, all at different volumes. So I sort of know exactly who’s speaking and on what channel based purely on the volume. The most important things are loud and the less important things are quiet.” All the while McMillan is looking at the gap between Antonelli and the leader, waiting for the right moment for the team to make its move.
The team holds its nerve until lap 27, when McMillan executes the plan. “I’d committed pretty much as soon as we started the lap. So, then I press a couple of intercom channels and say, ‘pit stop imminent: red,’ which is Kimi’s color,” he says. In those moments, McMillan says, the radio chatter dies down and the pit goes silent. “If you speak, you can only say important things. So don’t speak to me unless it’s important to this stop… I can still abandon it right up until the last minute, but at this point it will happen if I don’t say anything else.”
McMillan doesn’t say anything else. Antonelli comes in, the pit stop is flawless and the Italian teenager drives a perfect lap. Most importantly it doesn’t rain heavily. The undercut means Antonelli manages to edge ahead and take the lead, which he holds for the rest of the race. “We threaded that needle in Miami perfectly,” says McMillan.
F1 is a different sport than it was a decade ago and not just because of the technology. Netflix’s smash hit Drive to Survive reality show has opened it up to a huge new audience, much younger than the one it traditionally attracts. The drivers enjoy a turbocharged celebrity status. But in Miami, Kimi Antonelli is gracious in praising the team behind him who played such a vital, unseen role in engineering his victory. “We are working super hard and the team is doing an incredible job,” Antonelli said after the race. “They did a great strategy, we did a massive undercut and then we managed to bring it home, even though it was not easy.”
Mercedes’ team of engineers quietly pack up their trucks, leave Florida and move on to the next meeting. For McMillan, every race is a new set of data points to analyze. No two races, not even two on the same circuit, are ever the same. But Miami proves just how vital data, and the team analyzing it behind the scenes, have now become for F1. “We always joke that racing drivers win races and strategists lose races, but Kimi was very complimentary of the strategy,” McMillan says, smiling. “We will definitely claim that one.” ●
Kimi Antonelli battles for the lead at the Formula 1 Grand Prix at Miami International Autodrome. Photo credit: Sona Maleterova/LAT Images