Sandeep

Resume

A comprehensive view of my technical experience and education.

Download PDF

Technical Skills

Machine Learning & AI

  • Deep Learning (PyTorch, TensorFlow)
  • Natural Language Processing (NLP)
  • Computer Vision
  • Time-Series Forecasting (Scikit-learn)
  • RAG Architectures & Vector Search (FAISS)

Software Engineering

  • Full-Stack Web (React, Next.js, Node.js)
  • Languages: Python, TypeScript, JavaScript, SQL
  • Cloud & APIs: RESTful architecture, Deployment
  • Security & Quality Assurance
  • Database Management (SQL/NoSQL)

Professional Experience

Founder & Product Engineer at Skilvi

2026 – Present
  • Architected and deployed a production-grade LMS ecosystem to handle end-to-end student lifecycles without manual intervention.
  • Integrated automated payment processing via Razorpay and on-chain verifiable credential issuance.

Software Engineering Intern at Benaka Electronics

2025
  • Cut manual planning time on steel-coil slitting with a custom OR-Tools optimization engine.
  • Delivered and integrated the scheduling algorithm across 5 certified production phases.

Freelance Systems Builder

2023 – Present
  • GutBot RAG Deployment: Hardened an enterprise healthcare chatbot for production deployment on AWS EC2, strictly anchoring model responses to retrieved medical documents.
  • KLE SCP College: Executed a full institutional CMS rebuild using Grav CMS, resolving administrative bottlenecks for content management.
  • Spa/Fitness Booking System: Built a complete booking and scheduling system that eliminated double-bookings and manual calendar management for the client.

Publications & Research

FusioNet-DR

Dual-stream spatial-frequency framework

A dual-stream network that reads retinal images two ways at once — spatially and in the frequency domain — then fuses them with attention to grade diabetic retinopathy severity as an ordinal problem.

CBAM-CNN-BiLSTM

ECG arrhythmia classification

ECG classification with a debugging story: bypassed a standard library parsing bug by writing a custom binary .atr parser to get clean ground-truth labels before the model ever saw the data.

STAMP-Net

Oral cancer detection

Whole-slide pathology images too large for CNNs solved with attention-based multiple-instance learning, plus an adversarial mechanism that strips out stain-color bias.

B.E. in Artificial Intelligence & Data Science

Ramaiah Institute of Technology, Bengaluru (Expected 2027)

Diploma in Computer Science Engineering

KLE's CB Kolli Polytechnic, Haveri (2021 – 2024)

CGPA: 9.66