About Me
Hi, I am Aditya. Pleased to meet you.
I am an AI Software Engineer with 3+ years of experience building intelligent systems. I currently work at Appteon Inc., where I develop LLM-powered medical assistants with custom RAG pipelines. I recently graduated with a Master of Science in Computer Science from Emory University (GPA: 3.8). Before that, I am proud to say that I graduated summa cum laude with a Bachelor of Engineering in Computer Engineering from Devi Ahilya University.
I put my best into every line of code I write, striving to solve problems through ingenuity and diligence. I am naturally curious, confidently perseverant and constantly working to improve my skill-set one software at a time.
When I'm not coding, you can find me horseback riding, brushing up on my history knowledge, or swimming. I'm also an avid reader and enjoy writing in my free time. I'm always on the lookout for new challenges and opportunities to learn and grow.
Why programming?
Programmers are not coders who solve problems. Programmers are problem solvers who write code.
For me, programming is not just about writing code; it's about being a problem solver. Coding just happens to be the medium through which I solve problems. I love the challenge of taking a complex problem and breaking it down into smaller, more manageable pieces. I enjoy the process of designing elegant solutions and seeing them come to life in the form of working software. Programming allows me to be creative, analytical, and logical all at the same time. It's a field that constantly challenges me to learn and grow, and I find that incredibly rewarding.
I've wanted to become a software developer for as long as I can remember. While growing up, I was obsessed with computers and wanted to create my own one day. In high school, I excelled in classes like math and physics, which reassured me that becoming a software developer was the right career choice for me. Problem solving is something which comes naturally to me. I have an innate skill to look at any problem from different perspectives and come up with ingenious solutions.
Thank you for taking the time to learn more about me. I'm excited about the potential to collaborate on impactful projects and contribute to the ever-evolving field of software engineering.
Education
-
Master of Science in Computer ScienceEmory UniversityMay 2025
GPA: 3.8/4
Received a merit scholarship to attend the program
-
Devi Ahilya University2023Bachelor of Engineering in Computer EngineeringCGPA: 8.68/10; Class Rank: 3/150; graduated summa cum laude
Contact
Hey! Lets create something together :) Feel free to reach me on these handles
Research
-
Quantum Circuits in Action: Defending Neural Networks from Adversarial Attacks
- Evaluated adversarial robustness on the MNIST dataset by applying diverse attack methods (FGSM, PGD, SINIFGSM, VNIFGSM) using the Torchattacks library on both classical CNNs and Quantum Neural Networks (QNNs).
- Designed and simulated 8 QNN architectures (linear, star, random, and full entanglement etc.) with Cirq, demonstrating that quantum models can exhibit up to 6.25% improved resistance against complex adversarial perturbations compared to baseline CNNs.
- Developed a noise-augmented training strategy (using Salt-and-Pepper and Gaussian noise) that enhanced CNN accuracy by 3-10% and QNN accuracy by 2-6%, significantly bolstering model resilience against adversarial attacks.
- Note: On-going project with plans to publish in a top journal.
-
Concordance in Machine Learning and Deep Learning for Breast Cancer Screening
- Enhanced tumor detection accuracy to 77% with 91% AUC by fine-tuning ResNet50 and InceptionNetV2 models for breast cancer screening, leveraging Java and Python for model optimization.
- Processed and integrated 5TB of image and clinical data by creating end-to-end pipelines, ensuring seamless system integration and efficient data handling using ETL processes.
- Improved diagnostic prediction by implementing Naïve Bayes, SVMs, kNNs, Decision Trees, and Logistic Regression, enhancing system integration and leveraging SQL for data manipulation.
Click to view the site
Work
Download Resume
-
Appteon Inc.
AI Software EngineerJul 2025 - Present- Engineered an LLM-powered medical assistant with a custom RAG pipeline, automating patient data review with diagnosis suggestions and medication conflict detection across 600+ cases weekly.
- Fine-tuned AI models on AWS SageMaker using Python and PyTorch, integrating them into a conversational pipeline with WebSockets and AWS Transcribe to process doctor–patient dialogues, and generate clinical notes.
- Developed and deployed a containerized full-stack platform (React, Next.js, Bun, Docker, AWS EC2, ECR, ECS) with CI/CD pipelines across three environments, documenting end-to-end workflows to ensure stable and efficient delivery of the medical assistant system.
- Built TypeScript REST APIs for clinical workflows. Implemented OAuth2/OIDC user authentication via Amazon Cognito (JWT/JWKS) and policy‑driven RBAC middleware to enforce least‑privilege, auditable access.
- Collaborated closely with medical professionals to ensure outputs were interpretable and clinically relevant. Led training sessions and created non-technical walkthroughs to help clinician teams adopt new workflows seamlessly.
-
Emory University
AI Software EngineerMay 2024 - May 2025- Fine-tuned and deployed LLaMA 70B on a Flask server to power an AI-assisted screening system for evaluating applications. Reduced review time by 66% (from ~30 min. to ~10 min. per applicant) and saved ~$50,000 annually.
- Developed a faculty management system to track and approve leaves, performance reviews, awards, and tenure progression, streamlining administrative processes for 5,000+ faculty members, using React.js, Vite, Remix, and Next.js.
- Designed and implemented automatic grading software in React.js and Node.js for Python and Java assignments, automating grading for 300+ students and reducing grading time by 50% for faculty and TAs.
-
Watto AI (Y Combinator S23)
Software Development InternJun 2023 - Aug 2023- Used React.js, Next.js, TypeScript, and CSS to develop end-to-end features for 5+ core modules of an AI-assisted document editor, including document hub, forms, and outline editor, improving workflow efficiency for 200+ users.
- Implemented a real-time outline feature, allowing users to instantly visualize and restructure their document hierarchy while receiving AI-driven suggestions, reducing revisions and API calls by 58%.
-
Rakuten
Software Development InternJan 2023 - May 2023- Used Python and C++ to develop 50+ APIs for an AI-powered network capacity manager, automating key operations and improving system efficiency.
- Developed Shell and Python scripts to automate codebase setup, dummy data generation, and database querying, achieving a 50% reduction in setup and execution time and significantly streamlining testing pipelines on new systems.
-
workat.tech
Software Development InternMar 2022 - Jun 2022- Designed and developed a user profile page for 50,000+ users, featuring problem distribution, rank cards, progress tracking, and a submission heat map. Built an integrated resume generator that extracts coding profile data to generate a structured 1-page resume with language proficiency, past roles, and education details.
- Engineered a problem bookmarking system to categorize 300+ problems across 4 difficulty levels and 14 topics. Developed an intelligent problem recommender that suggests similar problems upon correct submissions and easier alternatives for incorrect attempts.
- Built a salary comparison tool used by 100,000+ employees to benchmark compensation, benefits, and industry trends across 25+ companies. Enabled precise salary analysis with interactive insights, empowering users to make informed career decisions.
Testimonials
Aditya worked with us as a fullstack engineering intern and built our user public profile pages and picked up a few smaller projects as well. He is a quick learner and a fast executor. He started contributing from day 1 without any background in React, Express, and MySQL before that. He is a strong communicator and asks the right questions to get unblocked and progress. I'm sure he would do impactful work wherever he joins and would be a great addition to the team/company.
Aditya is a great Software Engineer. At workat.tech, he distinguished himself by consistently developing exceptionally well-engineered products. As an intern, he has worked on developing the public profile page along with other projects. He demonstrated exemplary problem-solving skills and was always ready to pick up additional responsibilities. In addition to being an excellent communicator, he is a fast learner who displayed a keen eagerness to study new technologies. From day 1, he showed this ability by contributing and learning on the fly, even though he had no prior experience in some of the frameworks we used. Aditya is a pleasure to work with and I am positive that he would be a great asset to any team. I would strongly recommend him.
Aditya is an amazing person who is keen to learn and take up all the challenges. While working with him, he has demonstrated that he can learn and grow quickly beyond expectations. He is also good at communicating relevant things and makes sure that he is asking the right questions and that they are answered. His style of work and his passion for the same make him stand out from others. I can vouch for him any day and would love to work with him in the future.
I am amazed by Aditya's ability to learn a new skill in such a short span of time. He is a highly focused person who is full of energy. His energy to make things happen is contagious and it helps to achieve greater goals. The in-depth technical knowledge he possesses is immense on C++, web development, problem solving, Java and SQL. He spends his time on understanding the system and its effects and always comes up with the solution. He has a great attitude and is always eager to learn. I am confident Aditya will be a great asset for any team.
Aditya is one of a gem, having a great knowledge of Data structures and algorithm and outstanding in high level languages especially C++, Java and python. He is really keen to learn new things, bring up innovative ideas and does not shy away from hardwork, will strongly recommend him.
Mr. Prakash has in-depth technical knowledge and an attitude to take on challenges, finding unique yet simple and intuitive ways to solve complex problems. He is quite innovative. While developing and designing our website, we relied heavily on his inputs, ideas and solutions. He is extremely diligent and I am impressed with his dedication to work, and his ability to deliver under deadlines. He has shown professional competency and exceeded my expectations while performing his role as a software developer.
On top of this, Mr. Prakash is an exceptional communicator and his skills, coupled with his perseverance have made him one of the brightest developers we have worked with. I believe Mr. Prakash will be a brilliant asset for any organization. I wish him all the best for his future endeavours.
Skills
LanguagesLibraries & Frameworks
Databases
Projects
-
Canvas MCP Assistant
- Improved accessibility of AI-driven tools for students by developing a Python tool that creates an MCP-compliant server integrating AI assistants with Canvas LMS, structuring course data into knowledge graphs and storing it in SQLite.
- Built an AI-powered lecture material retrieval system, enabling instant access to summarized content and lecture insights, improving revision speed by 2× for the average student and ensuring comprehensive study resources for students.
-
Intelligent Movie Recommendation System
- Architected and developed a full-stack Movie Recommender System using Remix, React.js, Flask and PostgreSQL with advanced caching strategies using Redis.js to achieve an 85% cache hit rate, which reduced redundant database queries by 40%.
- Integrated third-party TMDB API to aggregate a comprehensive movie database and implemented a custom indexing strategy that cached the 200 most frequently accessed movies, reducing query response times by 80%.
- Achieved a 95% user satisfaction rating by conducting iterative usability tests, gathering actionable feedback, and refining both the interface and functionality to create a more intuitive UI/UX and engaging features.
Click to view the site -
Sorting Visualizer
A simple JavaScript application that visualizes sorting algorithms. Featuring a clean, intuitive, and minimalist UI, the application is easy to navigate and use. Built for use by developers and educators alike to enhance their own (or students') understanding of these algorithms.
Code | Website
Click to view the site