re:Invent 2024

Experiences as a Tech Intern at Caylent

Culture
Generative AI & LLMOps

Read about the experiences our summer technology fellow had at Caylent, where she explored cloud computing, generative AI, web development, and more.

Hi everyone, I’m Padma and I’m a rising senior at UC Irvine studying computer science and engineering. This summer, I had the opportunity to be a technology fellow at Caylent! I was also a hackNY Fellow, which connected me with a community of tech interns in New York City. Between my internship, the fellowship, and NYC, I had an incredible summer. I’ll share more about my experience in this blogpost!

Coming into the internship at Caylent, I had some exposure to AWS through my prior internships but didn’t really dive into their features beyond storage. I especially had no knowledge regarding their generative AI features, which Caylent leverages to improve clients’ infrastructures. Knowing the impact of cloud computing and generative AI, I was excited to be working at this company. Here are some things I worked on:

Benchmarking LLM Models

I worked on some benchmarking tools in Python aimed to assess foundation models (such as Claude and Sonnet) deployed on various cloud platforms, for scalability and cost efficiency. The existing benchmarking tools supported limited cloud platforms, involved calls to deprecated APIs, and didn’t take advantage of multi-threading to reduce evaluation time. I also added support for adjusting different hyperparameters, trying to find a way to reduce latency without sacrificing performance. Below, I’ve included one result from a preliminary draft of some tests I wrote to see whether different methods of clamping output tokens could reduce latency. In building these tools and writing these tests, I gained insight into large language models, use cases, and generative AI workflows.

Web Development

Additionally, I got some front-end and back-end experience for web development. I worked on adding additional features to Bedrock Playground, a website which enables clients to visualize, test, and compare foundation models deployed on AWS Bedrock. I included a screenshot of the website down below. Using React and Typescript, I implemented new features such as prompt saving and loading. These updates enabled users to easily save and quickly reload their prompts when comparing different foundation models, resulting in a more efficient and user-friendly experience.

Client Meetings

I also enjoyed shadowing Randall Hunt, VP of Cloud Strategy and Innovation, in his meetings- particularly with clients. I included a screenshot of a meeting with my boss below! In doing so, I gained more understanding about leveraging cloud technologies and generative AI to address client needs and drive innovation. I learned about trends and best practices in AWS services, and how to integrate these technologies into client solutions.

Other Takeaways

Throughout this summer, I’ve learned a lot about leveraging cloud services and generative AI to drive customer solutions. Beyond the technical skills, I also learned the importance of effective communication—specifically, the value of asking for help when I’m stuck on an issue for an extended period. I often felt that I should find a solution on my own rather than bothering busy coworkers or my supervisor. However, I’ve discovered that the people around me are an immense source of knowledge and are always ready to assist. I’m lucky to have been in welcoming and inclusive environments, where I can ask for help to move past any roadblocks. Through socials, work meetings and networking events, I’ve seen the value in engaging with those around me to gain diverse perspectives and insights.

hackNY Fellowship

Although my internship was remote, I was in New York City for the summer - which I was so incredibly happy about. I was in the 2024 hackNY fellowship, so I joined a co-living community of tech interns in NYC (pictured above!). The fellowship aims to empower the next generation of responsible technologists, and I felt lucky to be part of a diverse and inclusive community. While I wasn’t super excited to live in a dorm room again, I am so incredibly grateful for this summer and came to love living there with 20 built-in friends. As part of the fellowship, we had the opportunity to attend networking events, fun socials, and speaker series. I particularly enjoyed hearing from investigative journalists, venture capitalists, startup founders, and more. As a result, I learned about different technology trends and how to navigate my career. Specifically, it really made me inspired to pursue my personal interests, network with my community, and think about projects I’d like to work on. Between the fellows and the alumni, it was very inspiring to be surrounded by ambitious hackers. My summer was incredible, filled with enriching experiences from my internship and the fellowship, as well as exploring the city with new friends. I’ll always be grateful for it.

Join Caylent

If you're passionate about innovation and eager to build exciting new things, Caylent is the place where you can make a real impact. Explore our job openings and take the next step in your career with us!

Culture
Generative AI & LLMOps
Padma Iyengar

Padma Iyengar

Padma is a Computer Science and Engineering student at UC Irvine with a deep interest in software engineering, cloud technologies, and AI/ML. This past summer, she was a Summer Tech Fellow at Caylent working under Randall Hunt, VP of Cloud Strategy and Innovation. She enjoys tackling complex challenges and leveraging tech to build innovative and impactful solutions.

View Padma's articles

Accelerate your cloud native journey

Leveraging our deep experience and patterns

Get in touch

Related Blog Posts

Beyond the Hype - Evaluating DeepSeek's R1

DeepSeek’s R1 is making waves, but is it truly a game-changer? In this blog, we clear the smoke, evaluating R1’s real impact, efficiency gains, and limitations. We also explore how organizations should think about R1 as they look to leverage AI responsibly.

Generative AI & LLMOps

Getting Started with Agentic AI on AWS

Whether you're new to AI agents or looking to optimize your existing solutions, this blog provides valuable insights into everything from Retrieval-Augmented Generation (RAG) and knowledge bases to multi-agent orchestration and practical use cases, helping you make informed decisions about implementing AI agents in your organization.

Generative AI & LLMOps

Chatbot Design: Why Data Preprocessing is Critical

Chatbots often fall short, with 48% of users reporting they fail to solve issues. A chatbot's effectiveness depends on the data it can access, making data pre-processing essential, and success starts with understanding your use cases to ensure the right data is available.

Data Modernization & Analytics
Generative AI & LLMOps