Maria Beatriz Silva

I am a Presidential Honors Scholar studying Computer Science at NYU’s Courant Institute with a minor in Mathematics. As a Research Assistant at NYU’s Immersive Computing Lab, I work on problems at the intersection of computer graphics, human perception, and machine learning. My work is driven by the commitment to ensure technology is developed with the needs of its users in mind and by the desire to reshape who gets to participate in and benefit from technological innovation.

2 minute read

As my summer internship at Duolingo comes to a close, I’m reflecting on my experience working on the Design Accelerator Area team. This was my second summer at Duolingo, and getting to work on design systems and internal tooling gave me a completely different perspective on how product development works at scale.

What I Worked On

This summer, I tackled three main projects that improved workflows for designers, engineers, and animators across the company:

Redesigning the Animation Preview Tool
I redesigned Duolingo’s internal animation preview tool, which enabled 400+ previously inaccessible animations to be visualized by the team. This involved refactoring legacy code and collaborating closely with the design team to improve the UI. It was incredibly rewarding to see something I built immediately improve daily workflows for so many people.

Revamping Component Documentation
I revamped Duolingo’s component documentation platform by making the avatar preview page interactive and fully compliant with our design system. The goal was to significantly improve developer usability while ensuring everything aligned with internal design standards.

AI-Generated Image Evaluation
I led and launched Duolingo’s first experiment in AI-generated image evaluation by building a prompt adherence filter using GPT APIs. This involved generating synthetic data for model testing, running statistical evaluations, and iteratively optimizing prompt performance. It was exciting to work on the cutting edge of how AI tooling can improve creative workflows.

What I Learned

Working on design systems and AI design tools taught me to think differently about software engineering. Every decision affects countless developers and designers downstream, so code quality, documentation, and API design matter even more than usual. I learned to:

  • Balance maintaining consistency across a large codebase while enabling flexibility for different use cases
  • Collaborate effectively with designers to translate visual requirements into robust technical implementations
  • Think about developer experience as a first-class concern, not an afterthought
  • Appreciate the impact that good internal tooling has on team productivity

The Experience

Duolingo’s culture of experimentation and user-focused design really resonated with me. The team’s commitment to making language learning accessible to everyone mirrors my own goals in research—creating technology that serves real people’s needs.

Being selected for this internship reinforced my interest in building systems that empower others. Whether it’s internal tools for developers or research systems for scientists, I’m drawn to work that multiplies other people’s effectiveness.

Grateful for the opportunity and to everyone on the Design Accelerator Area team who made this summer so valuable!

Interested in internships at Duolingo? Feel free to reach out—I’m happy to share more about my experience!

You may also enjoy