With no prior aerospace knowledge or experience, my teammate and I stayed up all night learning about the HTF7000 engine, which then allowed us to ideate the redesign.

Talking to mentors, refining our ideas and ensuring we understand the intricacies of turbofan engines.

Self-teaching myself necessary thermal and fluid, deriving formulas and building the core mathematical foundation for our project, validated by my teammates.

Writing python script to optimize our numbers and get real value for our design.

Providing data to the designer for presentation, and practicing our pitch. I was the main presenter, so I practiced for a long time to ensure clarity and confidence.

Final presentation. Our team was selected to give the presentation again in front of Honeywell engineers, and this is when we won 4th place! Our team also won a total of $5000.

I was trained in multiple lab protocols, including radiation safety and sample handling. I learned analysis techniques such as Rutherford Backscattering Spectrometry (RBS) and Particle-Induced X-ray Emission(PIXE).

Under supervision, I learnt to open and perform maintenance tasks on high-vacuum systems. Multiples such vacuums were used in the accelerator. I also assisted in troubleshooting the ion beam accelerator, helping disassemble components to understand its mechanics.

Mastered the primary software tools for RBS data analysis, including xRUMP and SIMNRA. I later used these skills to analyze data from NASA's Genesis mission, where I used to work earlier.

As a team of six, we brainstormed ideas, and came up with many concepts. After some discussion, we settled on BeastWatch, an AI-powered wildlife safety app.

We split up responsibilities, and I took to building the AI pipeline. We selected the Faster R-CNN model for object detection and Gemini 2.0 for analysis and guidance generation.

We frantically worked to integrate the models as time grew short. I got the pipeline done, and my teammates were done fine-tuning our AI models. We integrated everything and prepared for submission.

Our team successfully built and demonstrated a complete, functional product in just 4 hours, showcasing a working AI pipeline from detection to generative AI-based safety advice.