open to work · available immediately
I build LLM-powered applications, retrieval pipelines, and the backends underneath them. My research on detecting autism from gaze patterns is published at IEEE OTCON-2025.
A medallion pipeline that answers seven business questions — and refuses to answer where the data can't support one.
PySpark · Aurora PostgreSQL · S3 Parquet · AWS EKS · AWS Lambda · Terraform · React · Jupyter
Built for Citi's coding workshop, against a provided brief and repository scaffold. The pipeline, serving layer, API and interface are my work — 43 commits.
A non-invasive screening pipeline that reads gaze behaviour instead of administering a questionnaire.
Python · TensorFlow · ResNet18 · Random Forest · scikit-learn
An LLM agent that reviews pull requests and returns structured, actionable feedback.
TypeScript · Node.js · Express · Google Gemini API · Supabase · REST
Neural retrieval that encodes queries and documents independently, so search cost stops scaling with the corpus.
Python · Embeddings · Vector search · RAG · PyTorch
Ten-plus REST APIs modelled on real lending workflows, with authorisation enforced where it belongs.
Java · Spring Boot · React · MongoDB · Docker · JWT
IEEE OTCON-2025 ·
A non-invasive machine-learning approach to autism spectrum screening that classifies subjects from eye-tracking data, using gaze patterns and fixation duration as behavioural biomarkers rather than clinician-administered instruments.
Prime Global Workforce
Vishwakarma Institute of Technology, Pune
CGPA 8.69 · Data Structures & Algorithms · DBMS · Operating Systems · Computer Networks · OOP · Machine Learning
certifications
leadership
Secretary · SWDC, VIT Pune
Led 200+ volunteers and 30+ coordinators across flagship social campaigns and campus events.
Corporal · National Cadet Corps
Completed national-level endurance camps, demonstrating leadership and discipline under pressure.
AI / LLM
RAG pipelines, Two-tower retrieval, Prompt engineering, LLM orchestration, Google Gemini API, Embeddings, Vector search, TensorFlow, PyTorch, scikit-learn
Languages
Python, Java, TypeScript, JavaScript, SQL, C, C++
Backend
REST APIs, Node.js, Express.js, Spring Boot, Django, Microservices, JWT auth
Databases
MongoDB, MySQL, PostgreSQL, Supabase, Vector databases
Cloud & DevOps
AWS EC2, AWS S3, Docker, Git
Frontend
React, Next.js, Tailwind CSS
A practical workflow for moving from idea to shipped product: requirements, data flow, UI structure, testing, and deployment.
Notes on designing web products that stay maintainable as features, users, and deployment complexity grow.
A practical look at turning model experiments into usable pipelines with clear metrics and failure cases.
How to present projects, engineering decisions, and proof of work without overloading the page.
// available immediately
B.Tech complete, June 2026. Available immediately for full-stack, backend, and AI engineering roles. The fastest way to reach me is email — I reply to everything.