ADYA PRASAD

Reinforcement learning • Agent Orchestration • LLM interpretability

ABOUT ME

Backend Engineer with 6 years of Python expertise, skilled in scalable system design with a primary focus on ML research. My works focus on reinforcement learning, multi-agent orchestration, fine tuning and mechanistic interpretability, not because these are trending fields, but rather my interest in them grew after reading the research papers (Google Deepmind, Deepseek, and Claude) and news, They are closest to the subject I like to get in depth.
On the applied side, I'm love building and tuning models to create helpful wrapper apps with it and solve Indian market problems. I prefer building platforms and systems rather than just creating an application. I am currently seeking a research affiliation or research internship to contribute and learn more: RL and multimodal ai architectures. Ready to put in effort, take charges, and align with the needs of practical research!

A soul, interested in the intersection of backend dev, ML research, data story telling, and entrepreneurship

EXPERIENCES

Applied AI Research Intern

2026 May - Present

Working on mechanistic interpretability research project
Problem Statement: Detecting Chain-of-Thought Unfaithfulness from ResidualStream Trajectories. Trains lightweight probes that compare a model's verbalized chain-of-thought to its residual-stream trajectory during the same forward pass, yielding an internal faithfulness signal that complements external CoT monitors and transfers across hidden-objective, dishonesty, decomposition, and CoT-control benchmarks.

Founder: Creators AI Lab

2023 - 2025 Nov

Innovating and building ai suite for content creation with my experience of ai ml researches. Primary focusing on content creators and influencers
Researches and applications under Creators AI Lab: 'Cupid AI suite for content creation', 'Luffy Create' video creation app, 'Neel Voice' for text to speech voice cloning.

Full Stack Developer

2023 - 2025 Nov

Collaborated with the founder, assisting staffs and marketing team to develop a patient-centric website, for ease of adaptability, used the Wordpress cms with a custom plugin and design a appointment booking service and pre-/post-care guide pipeline.
Build a patient feedback and assistance loop to seek feedback, provide treatment guidance, and improve patient engagement.
With an optimised website and integrated feedback with marketing workflows, resulting in a 25% increase in clinic footfall through organic and paid digital marketing conversions

Freelance web and app developer

2021 - present

Worked with local enterprises, proprietors, and small businesses to understand requirements, analyse market and competitor insights, and deliver tailored, researched data, e-commerce applications, web platforms, and automation solutions (using n8n) aligned with their vision.
Successfully delivered 10+ projects, including: Rajeshwari Asha Enterprises (application for monitoring orders and throughput), Aditya Pathology (automated scheduling and customer notification system), Yatidhara [fmcg company]
Learn to handle end-to-end development lifecycle across multiple concurrent projects, communication with the clients, and understood problem faced by small cities founder

Founder (Developer and Author) of a STEM educational website: indiecore.in

2022 March - 2024

Run and manage a STEM educational website, specially focused on high school and intermediate students to provide free of cost study material for their exam preparation, computer skills, and reasoning skills development
Create 500+ resources and materials: blogs, webstories, quizzes, mock tests, pdfs and flashcards. Achieved 1 million plus impressions and than 200k traffic
Built with WordPress and custom plugins, Grow the application with 'Search Engine Optimization' and organic marketing os social platforms and forums

OPEN SOURCE CONTRIBUTIONS

Hugging Face: Peft

1. Resolve issue #2944: ensure_weight_tying respects config + improved tests {PR #3171}
updated src/peft/utils/other.py in the set_additional_trainable_modules() and _get_module_names_tied_with_embedding() functions to respect the model config and also create test file

2. Experiment method comparison #2310 : adaptation_prompt {PR #3301}

Conduct experiement with finetuning, benchmarking the LLaMA-Adapter (adaptation_prompt) for Conversation AI and Math reasoning. I configured custom adapter config and training parameter with the Llama-3.2-3B model, ran multiple training pipelines on the MetaMathQA dataset, and evaluated its memory efficiency, accuracy, loss and reasoning retention against baseline methods to provide benchmarked result to community.

Unsloth

https://github.com/unslothai/unsloth/issues/224 {➚}
solved the issue of breaking of exporting model to Colab.

ARTICLES AND PUBLICATIONS

1. AushadiNet-GATv2: Graph Attention Network for Predicting Drug-Drug Interactions in Polypharmacy

India AI

I researched and presented AushadhiNet-GATv2, a graph neural network architecture for predicting drug-drug interactions in polypharmacy. System addresses critical limitations of existing DDI prediction methods through multi-view molecular representation learning, hierarchical GATv2 message passing with residual connections, dual-head classification for interaction detection and mechanism prediction, and integration with patient-specific cardiovascular risk profiling

2. How to Build and Deploy Ingress Microservices in Kubernetes

DEV .to

Microservices is a common approach used to design scalable software systems. Ways to build and deploy microservices in Kubernetes with Ingress for HTTP routing using a docker image from the docker hub repository and building yml files for both services.

PROJECTS

Cupid: Agentic Social Media Content Generation Platform

A multi-agent system to generate platform-specific social content from natural-language prompts. Four LangGraph agents coordinate the pipeline: supervisor agent, personalization agent, research agent, and composer agent. The personalization agent decomposes user intent into five orthogonal search queries, the research agent runs parallel web retrieval through DuckDuckGo with trafilatura-based content extraction, the composer agent distills sources into atomic facts and generates three angle-diverse variants in parallel, and the trends service handles scheduled background ingestion from Google News RSS ranking articles per-user with BM25 and recency decay, hybrid memory layer and LLM chain for fallback: Groq, HuggingFace and local heuristics.

multi-agent orchestrationMCPRAGLangchain

AushadhiNet-GATv2 DDI Model

AushadhiNet-GATv2 is a graph neural network model that predicts drug-pair interactions with probability scores and classifies interaction types (potential adverse drug reactions) across 86 mechanisms. The system alerts physicians and patients before prescribing or taking medications, preventing harmful drug combinations.

#Research ProjectGNNDrug MoleculesDrug Interaction Prediction

Luffy Create: Video Creation and Editing Application

A lightweight, open-source desktop app for making animated videos for technical and educational content. Code walkthroughs, system-design diagrams, and slide-based animations — with frame control, Agentic AI help, automatic subtitles feature and mutliple format export. Fully offline, no account required.
Built on Electron, ffmpeg and ai api.

desktop appmultimedia processingstream management

GLC-Platform

Green Loan Cycle platform streamlines ESG-linked loan assessments automatically, identifying and measuring key metrics, making data capture on performance 30% easier with LMA framework and AI agents. Features: loan data resolution, loan assessment, sustainability checks, key stakeholder evaluation, loan balance sheet generation, and AI-assisted advice.

#Hackathon ProjectNLPFinancial AnalysisRAG

Self-learning, self driving car simulation with vanilla Javascript

Inspired by Dr. Radu Mariescu-Istodor, A pure JavaScript neural network system that learns to drive cars autonomously and avoid obstacles. AI Functions: Genetic Algorithm with mutation-based evolution, Population-based learning, Real-time neural network Visualisation, Fitness-driven selection for optimal performance

Autonomous SystemSelf driving carVanilla JS

A Educational and Exam Helping Website: indiecore.in

Developed and launch an educational STEM website using WordPress and custom plugins, achieve 1 million plus impressions with organic SEO. Featuring interactive quizzes, educational articles, and engaging web stories, CUET and SSC exams mock tests.

#Side HustleWordPress CMSSTEM websiteSEO

VIBE CODING PROJECTS

Mobi Flow: Type in your PC through phone from anywhere

Transform any article, text file, study resources, URL or direct text into interactive study materials: Summary, Flashcards, and Quizzes with live results and marks. Making learning interactive, evaluative and handy.

Hackathon ProjectAI Web ApplicationGemini Nano APIFetch API

Naina: Multimodel Assistant at Fingertips (Extension)

A multipurpose intelligent companion in your browser to boost productivity without distraction. With Multimodal intelligence, context awareness, local storage, and Dyslexia-friendly.

Hackathon ProjectChrome AI APIGemini Nano APIBrowser Extension

Social Media Inspired Fitness App

A fitness app for youth friends, inspired by social media. Contains daily exercise customization, stop watch, time duration, daily streaks, camera app with filters, in build music player, in built fitness video player.

Node jsvite jsTailwind CSSMedia Player

SKILLS AND TECH STACK

LANGUAGES:PythonTypeScriptR langJavaScriptSQL

FRAMEWORKS:FlaskDjangoFastAPIReact jsNext js

TOOLS:Apache Ecosystem (learning: Kafka, Spark, and Hadoop)Hugging Face EcosystemOllamaMongoDBPostmanPrometheusn8nCanva

DB:PostgreSQLSQLiteMongoDB RedisChromaDB

LIBRARY / MODULES:PyTorchTensorFlowNLTK (NLP)NumpyPandasMatplotlibPEFTTransformersOpenaiLangchainLlamaIndexSQLAlchemyChromaDB

PLATFORMS:DockerKubernetesAWS Ubuntu OSKali OS

EXTRACURRICULAR ACTIVITIES & ACHIEVEMENTS

Deloitte Australia Technology Job Simulation on Forage
- Develop a program to normalise different telemetry JSON data of IOT machine (Simple ETL pipelines)
- Craft a complete "software development proposal" for a real-time monitoring live dashboard
Teaching assistance for freshers, in fundamentals of computer application subject. Office hours work on managing course materials and leading discussion group.
Hackathon Winner: Bye to Beat on Devpost | Project: AushadhiNet-GATv2 DDI Model | Predicting Drug-Drug Interactions
200+ Submission Competitive Programming: HackerRank, LeetCode, CodeForces, and TensorTonic

LEARNINGS (EDUCATION)

St Thomas International School:

High School (9 and 10)
Intermediate (11 and 12).

VBSP University:

Bachelor of Science, Computer Science.

Harvard CS50x:

Computer Science, Cybersecurity, Artifical Intelligence and R*.

Master Diploma in Computer Application

from Amrtikosh Info-tech institute (duration: 2 years). Fundamentals of Computer Application, HTML, CSS, JS, TS, Bash Scripting, Web Development, MS Excel, and more

Certifications:

YouTube full course playlist I take: Standford C229 Machine Learning (Autumn 2018), Stanford CS230 Deep Learning (Autumn 2025), Standford CS224R Deep Reinforcement Learning (Spring 2025)
Introduction to Cloud Native DevOps Agile and NoSQL by IBM - [July 2024]
Introduction to Amazon EC2 by AWS Training - [Oct 2025]
Introduction to Amazon Simple Storage Service (S3) by AWS Training - [Oct 2025]
Amazon SageMaker AI Getting Started by AWS Training - [Oct 2025]
Build Your Own Chatbotby IBM SkillsBuild- [Jan 2025]
Market research by Great Learning - [May 2024]
Google Technical Writing Course One and Two by Google Developers - [June 2022]
Content Creation, Optimization, SEO and Strategies by HubSpot Academy

CONTACT ME

Hey you, I am very much interested in speaking with you, Feel free to contact me