Intern Series: Making an Impact as an Intern on MongoDB’s Driver Team

Joshua Fayer
January 16, 2020 | Updated: August 31, 2022
#Culture#EarlyTalentRecruiting

Sam Pal is a Computer Science major and Technology and Management minor at the University of Illinois at Urbana-Champaign. Her first foray into technology was a Girls Who Code immersion program one summer in high school, and she’s been committed to activism and technology ever since. In this interview, you will hear about Sam’s experiences as an engineering intern on MongoDB’s Driver team.

"Sam Pal"

Josh Fayer: What team did you intern on and what did your team do?

Sam Pal: My team worked on the Node.js Driver at MongoDB. The work consisted of programming in Node.js to not only maintain the driver and implement new features but also interact with actual users to make their hopes and aspirations for the driver a reality. We constantly looked through JIRA tickets and GitHub to proactively provide what our users needed and address improvements or issues they ask about--the driver itself is constantly being revamped, as it is one of the most widely used and also one of the first drivers to be implemented.

My team was incredibly impactful on my learning, both about how MongoDB development works internally as well as in the context of the driver and Node.js as a language. Furthermore, I learned big-picture skills like creating a proof-of-concept, many GitHub tips and tricks, and gained a ton of life and career advice.

JF: What was one of your favorite projects that you worked on?

SP: My assignment on the Drivers team was two-fold. For the first half of the internship, I on-boarded by getting myself familiar with the Node.js language; both its general semantics and structure of the language itself. Then I worked on tickets meant to further my understanding of the driver, specifically relating to our testing stack and learning the fundamentals behind how the driver tests are run.

For the latter half of the summer, my co-intern, Rosemary Yin, and I worked on a project to revamp our test runner on the Node.js Driver. This was an awesome (yet daunting) task because there was a lot to unpack in terms of dependencies. This is arguably where I felt I had the most ownership and value as an active contributor to the Node.js Driver for the summer.

JF: What is the culture like at MongoDB?

SP: The employees at MongoDB are open to idea-sharing-- they value providing feedback, and they are always willing to help. Everyone at MongoDB has a genuine interest in and dedication to the product as a whole. I think the rapid growth and necessary changes that MongoDB has undergone in the last couple of years is a testament to its uniqueness both in size and impact. Furthermore, being able and encouraged to attend MongoDB World 2019 as an intern shows MongoDB’s commitment to learning and growth for all its employees.

JF: How has the work at MongoDB challenged you, and what have you learned here?

SP: The work at MongoDB has been significant and interesting in every aspect. I came to the Drivers team wanting to make an impact beyond just committing code, and I feel as though I have done just that. Between interacting with real users and working on a project that will improve how we test the entire driver, I feel that in my 11 weeks at MongoDB, my work is valued. It was challenging to start with virtually no experience programming in Node.js and little experience with the driver, but, I now have a good understanding of MongoDB itself, and all the moving parts involved in the product.

JF: What was your favorite part about being an intern at MongoDB?

SP: My favorite part about interning at MongoDB was the people. I consistently had the opportunity for mentorship and growth because I was surrounded by incredibly smart, capable, and most importantly, fun-loving individuals. Additionally, there is an amazing culture of getting things done, and doing them well. There is a commitment to excellence that inspires me.

Interested in pursuing an internship at MongoDB? We have several open roles and would love for you to grow your career with us!

← Previous

How to Rock Your Customer Success Interview at MongoDB

Learn how to join our Customer Success team from Julia Prause, the Global Director of Customer Success at MongoDB.

January 15, 2020
Next →

Retrieval Augmented Generation for Claim Processing: Combining MongoDB Atlas Vector Search and Large Language Models

Following up on our previous blog, AI, Vectors, and the Future of Claims Processing: Why Insurance Needs to Understand The Power of Vector Databases , we’ll pick up the conversation right where we left it. We discussed extensively how Atlas Vector Search can benefit the claim process in insurance and briefly covered Retrieval Augmented Generation (RAG) and Large Language Models (LLMs). MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More One of the biggest challenges for claim adjusters is pulling and aggregating information from disparate systems and diverse data formats. PDFs of policy guidelines might be stored in a content-sharing platform, customer information locked in a legacy CRM, and claim-related pictures and voice reports in yet another tool. All of this data is not just fragmented across siloed sources and hard to find but also in formats that have been historically nearly impossible to index with traditional methods. Over the years, insurance companies have accumulated terabytes of unstructured data in their data stores but have failed to capitalize on the possibility of accessing and leveraging it to uncover business insights, deliver better customer experiences, and streamline operations. Some of our customers even admit they’re not fully aware of all the data in their archives. There’s a tremendous opportunity to leverage this unstructured data to benefit the insurer and its customers. Our image search post covered part of the solution to these challenges, opening the door to working more easily with unstructured data. RAG takes it a step further, integrating Atlas Vector Search and LLMs, thus allowing insurers to go beyond the limitations of baseline foundational models, making them context-aware by feeding them proprietary data. Figure 1 shows how the interaction works in practice: through a chat prompt, we can ask questions to the system, and the LLM returns answers to the user and shows what references it used to retrieve the information contained in the response. Great! We’ve got a nice UI, but how can we build an RAG application? Let’s open the hood and see what’s in it! Figure 1: UI of the claim adjuster RAG-powered chatbot Architecture and flow Before we start building our application, we need to ensure that our data is easily accessible and in one secure place. Operational Data Layers (ODLs) are the recommended pattern for wrangling data to create single views. This post walks the reader through the process of modernizing insurance data models with Relational Migrator, helping insurers migrate off legacy systems to create ODLs. Once the data is organized in our MongoDB collections and ready to be consumed, we can start architecting our solution. Building upon the schema developed in the image search post , we augment our documents by adding a few fields that will allow adjusters to ask more complex questions about the data and solve harder business challenges, such as resolving a claim in a fraction of the time with increased accuracy. Figure 2 shows the resulting document with two highlighted fields, “claimDescription” and its vector representation, “claimDescriptionEmbedding” . We can now create a Vector Search index on this array, a key step to facilitate retrieving the information fed to the LLM. Figure 2: document schema of the claim collection, the highlighted fields are used to retrieve the data that will be passed as context to the LLM Having prepared our data, building the RAG interaction is straightforward; refer to this GitHub repository for the implementation details. Here, we’ll just discuss the high-level architecture and the data flow, as shown in Figure 3 below: The user enters the prompt, a question in natural language. The prompt is vectorized and sent to Atlas Vector Search; similar documents are retrieved. The prompt and the retrieved documents are passed to the LLM as context. The LLM produces an answer to the user (in natural language), considering the context and the prompt. Figure 3: RAG architecture and interaction flow It is important to note how the semantics of the question are preserved throughout the different steps. The reference to “adverse weather” related accidents in the prompt is captured and passed to Atlas Vector Search, which surfaces claim documents whose claim description relates to similar concepts (e.g., rain) without needing to mention them explicitly. Finally, the LLM consumes the relevant documents to produce a context-aware question referencing rain, hail, and fire, as we’d expect based on the user's initial question. So what? To sum it all up, what’s the benefit of combining Atlas Vector Search and LLMs in a Claim Processing RAG application? Speed and accuracy: Having the data centrally organized and ready to be consumed by LLMs, adjusters can find all the necessary information in a fraction of the time. Flexibility: LLMs can answer a wide spectrum of questions, meaning applications require less upfront system design. There is no need to build custom APIs for each piece of information you’re trying to retrieve; just ask the LLM to do it for you. Natural interaction: Applications can be interrogated in plain English without programming skills or system training. Data accessibility: Insurers can finally leverage and explore unstructured data that was previously hard to access. Not just claim processing The same data model and architecture can serve additional personas and use cases within the organization: Customer Service: Operators can quickly pull customer data and answer complex questions without navigating different systems. For example, “Summarize this customer's past interactions,” “What coverages does this customer have?” or “What coverages can I recommend to this customer?” Customer self-service: Simplify your members’ experience by enabling them to ask questions themselves. For example, “My apartment is flooded. Am I covered?” or “How long do windshield repairs take on average?” Underwriting: Underwriters can quickly aggregate and summarize information, providing quotes in a fraction of the time. For example, “Summarize this customer claim history.” “I Am renewing a customer policy. What are the customer's current coverages? Pull everything related to the policy entity/customer. I need to get baseline info. Find relevant underwriting guidelines.” If you would like to discover more about Converged AI and Application Data Stores with MongoDB, take a look at the following resources: RAG for claim processing GitHub repository From Relational Databases to AI: An Insurance Data Modernization Journey Modernize your insurance data models with MongoDB and Relational Migrator

April 18, 2024