In Conversation with Parthsarthi Rawat: Making AI Practical for Youth Sports

Parthsarthi Rawat is part of a new generation of engineers turning complex technology into everyday tools. A computer vision specialist whose work has reached over six million users, Rawat has built AI-driven systems that make sports analytics more accessible to families, coaches, and young athletes.

An early win at the ASME Student Design Competition showed Rawat how technology could solve real-world problems. This saw him begin his career in Silicon Valley in mechanical engineering and robotics competitions. Since then, he has earned recognition from IEEE, helped secure multimillion-dollar funding rounds, and contributed to sports tech platforms that are changing how people experience youth athletics.

In this conversation, Rawat shares how his work bridges research and real life, what inspired his mission to make AI more human-centered, and where he sees the next frontier for sports technology.

Q: You’ve said your mission is to “pull AI out of research papers and make it useful for everyday people.” What inspired that goal? 

A: When I began my career, AI felt locked inside academic circles: papers, prototypes, and simulations. I wanted to change that. My journey started in mechanical engineering, not computer science. It was through robotics competitions, like the ASME Student Design Competition, that I saw how AI could solve real problems.

When my team won the ASME SDC in 2018, it was a turning point. I realized AI wasn’t just a research topic. It could directly improve people’s experiences. That motivated me to focus on applications that would reach ordinary users, not just engineers in a lab.

Q: Your early work in AI and computer vision earned recognition from IEEE. How did those experiences shape your technical approach? 

A: My first IEEE paper, which won the Best Paper Presentation Award at ICCAR 2020, gave me a strong sense of validation. Research teaches you how to break complex systems into smaller, solvable problems. It also forces you to be rigorous. AI is only as strong as its foundation.

That mindset still guides my work today. Whether I’m designing a neural network for sports analytics or building real-time video features, I always go back to the fundamentals. The math, the logic, the structure, that’s what ensures your AI model is not just impressive, but reliable.

Q: What drew you to the intersection of AI and sports technology? 

A: Sports offer something unique. You can see the impact of technology instantly. When a parent replays their child’s highlight moments or a coach uses data to plan the next game, the feedback is immediate and emotional.

At SportsVisio, I built the company’s AI pipeline and helped the team secure $3 million in seed funding in 2023. But what I missed was seeing the human reaction, how technology actually changes someone’s day. That’s what led me to GameChanger by Dick’s Sporting Goods, where the audience was already millions strong. I knew I could make AI feel personal and practical there.

Q: Tell us about FilmRoom. How does it use AI to make video analysis more accessible? 

A: FilmRoom is designed to give ESPN-style analysis to youth teams using nothing but a smartphone camera. We developed AI that automatically trims game footage, removing downtime, so instead of a three-hour video, you get the key highlights in minutes.

That process involves downtime classification, where the AI learns to identify moments with no action, like breaks or waiting between plays, and skips them automatically. It’s a simple idea, but it took deep computer vision work to get right.

Today, more than six million users are using FilmRoom, and we’ve expanded its features to other sports like baseball and basketball. Seeing families and coaches rely on it, that’s the most rewarding part.

Q: As someone building large-scale AI tools, how do you see the technology evolving over the next few years? 

A: AI is moving toward personalization. The next phase is context-aware AI, systems that adapt to individual users instead of just following generic models. We’re going to see more hybrid applications where AI quietly enhances day-to-day experiences without people even realizing it’s there.

In sports, that might mean personalized training insights or predictive feedback during games. In education, it could mean custom tutoring in real time. The key shift is that AI will no longer feel like “technology.” It will feel like assistance: natural, accessible, invisible.

Q: You’ve also served as a mentor for IEEE and major hackathons. What role do you see mentorship playing in AI’s growth? 

A: Mentorship is crucial. AI is expanding so quickly that the next generation needs more than technical knowledge; they need perspective. When I review papers or judge hackathons at places like MIT or Harvard, I see incredible talent. But I also see a hunger for guidance: how to take an idea from a prototype to a product that helps people.

If I can help younger engineers bridge that gap, that’s part of my responsibility. The future of AI depends not just on breakthroughs, but on people who understand why those breakthroughs matter.

Q: Finally, where do you see your own work heading next? 

A: My focus remains the same: to make AI as natural and helpful as unlocking your phone. I’m working on ways to extend these models beyond sports, into areas where people interact with video, movement, and data in everyday life.

AI shouldn’t intimidate anyone. It should empower them. Whether it’s helping a kid review their first home run or assisting a teacher in the classroom, my goal is to keep bringing AI closer to human experience.

Rawat’s story is a reminder that the most meaningful innovations often begin with a simple idea: that technology should serve people, not the other way around. From robotics labs to youth sports fields, his work continues to prove that AI’s future lies not just in intelligence, but in accessibility.