ADYA PRASAD
Reinforcement learning • Agent Orchestration • Post TrainingABOUT ME
Backend Engineer with 3 years of Python expertise, skilled in scalable backend system with a primary
focus
on ML research. My works focus on reinforcement learning, multi-agent orchestration,
and post training, not because these are trending
fields, but rather my interest in them grew after reading the research papers (Google Deepmind,
Deepseek, and Claude) and my works. They are closest to the subject I like to get in depth.
On the
applied side, 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 handle heavy backend and
AI research tasks. Ready to put in effort, take charges, and adapt 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 | BaseThesis Lab
May 2026 - Present
- Working on research: Evaluating Chain-of-Thought Unfaithfulness from Residual Stream Trajectories and linear probe
- Initiated and co-led an empirical research project investigating whether a model's internal residual-stream representations faithfully align with its verbalized chain-of-thought during reasoning task.
- Designed and curated a diverse evaluation dataset spanning mathematics, reasoning, history, and safety to improve statistical robustness and probe generalization. Scored AUROC 0.65, demonstrating residual-stream trajectories provide useful signals for detecting unfaithful reasoning on-going
Full Stack Developer | NowTreat Healthcare
Jun 2023 - Nov 2025
- Ownership of official website and integrate a patient post treatment care and booking service, along with feedback loop using WordPress CMS, and JavaScript to support post-treatment guidance, and improve patient engagement.
- Small team, high ownership! Along with marketing team and founder, designed an marketing funnel for better user experience and engagement and converting online traffic to potential patents. Collectively achieve 38% more engagement and 26% more footfall
Founder: Creators AI Lab
2026
Innovating and building ai suite (softwares) for content creation with my experience of
backend
development and ML engineering. Focus audience: content creators and influencers.
- Cupid AI Suite: An app with Swarm of AI agents for diverse and user
personalized research and content creations using LangGraph, FastAPI, API Services,
PostgreSQL, Redis, ChromaDB, and Docker.
Designed a multi-stage safety and response evaluation pipeline combining heuristic validation, policy checks, and quantitative monitoring metrices to filter user inputs and validate LLM outputs before responding to user. - Luffy Create:Luffy Create is a free and open source AI video editing, video
creation, image editing and graphic designing web app.
Luffy Create has been built with the principle of providing a lightweight and fast editing experience. Goal: Our aim is to make 'Luffy Create' the best editing app for animations, transitions, and effects.
Freelance Works (Developer)
2022 - present
- Yatidhara [FMCG]:Work with founder in supply chain of Ayurvedic and healthy (gift style) products. I work on designing premium healthy products (snacks) packaging and end to end ecommerce web development.
- Focus Point [Digital Library and Study Space]: Along with founder Mukesh Sonkar (a frontend engineer)and I (as a full stack developer) build platform (library marketplace). The Focuspoint serve as marketplace for both library owner and students. Library owner can list their library and students can find the best library as per their need in nearby
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
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.
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.
solved the issue of breaking of exporting model to Colab.
ARTICLES
1. AushadiNet-GATv2: Graph Attention Network for Predicting Drug-Drug Interactions in Polypharmacy
-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
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
Luffy Create: AI Video Creation App
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.
Built on Electron, ffmpeg and ai api.
desktop appmultimedia processingstream management
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
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
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
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
-
Founder (Developer and Author) of a STEM educational website: indiecore.in
- 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
- 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:
B.Tech(Computer Science & Engineering)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 programming, C, JavaScript, TypeScript, Bash Scripting, Web Development, Office Automation.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)
- 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