AI Engineer with less than a year in Deep Learning & Azure Deployment
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Final-year B.Tech Data Science student with hands-on experience building and deploying machine learning and deep learning systems in production environments. Designed and shipped an Azure-hosted medical image classification pipeline (EfficientNetB0, ResNet, DenseNet) achieving multi-class eye-disease detection, and developed a full-stack ML inference API (FastAPI + scikit-learn) for real-time stock market analysis. Comfortable across the end-to-end ML workflow - data preprocessing and model training. Developed a RAG system offline personal assistant with voice integration. Actively targeting AI/ML/Data Science internship roles where I can contribute to model development and scalable AI product delivery.
Malla Reddy College of Engineering, JNTU Hyderabad
B.Tech · Data Science
August 1, 2021 – June 30, 2025
Sri Chaitanya Junior Kalasala
Senior Secondary Education
June 1, 2019 – May 31, 2021
New Little Lilly High School
Secondary Education
June 1, 2018 – May 31, 2019
DeepDiabetic - Medical Image Classification for Diabetic Eye Disease Detection
June 23, 2026 – Present
Designed and trained a multi-class CNN pipeline to detect Diabetic Retinopathy, DME, Cataract, and Glaucoma from retinal fundus images. Implemented transfer learning with EfficientNetB0, ResNet, and DenseNet; applied image augmentation, preprocessing, and fine-tuning for improved generalisation. Deployed a live inference backend on Microsoft Azure (App Service + MySQL + Static Web Hosting), serving real-time predictions via REST API.
Personal AI Assistant (Local RAG + Voice Interface)
June 23, 2026 – Present
Developed an end-to-end offline AI assistant using a Retrieval-Augmented Generation (RAG) pipeline for context-aware question answering. Implemented PDF ingestion and preprocessing with chunking and semantic embeddings using Sentence Transformers. Built a high-performance vector search system using FAISS for efficient document retrieval. Integrated a local LLM (Mistral via Ollama) to generate accurate responses without relying on external APIs. Designed and implemented multi-turn conversational memory to support context-aware dialogue. Engineered voice interaction capabilities using Whisper (speech-to-text) and pyttsx3 (text-to-speech). Structured the project using a modular Python architecture for scalability and maintainability. Optimized system for low-latency inference and fully offline execution.
Cultural Fit Analysis
The candidate's academic projects showcase a proactive and self-driven approach to learning and applying advanced AI/ML concepts. The diversity in projects (medical image classification, local RAG assistant) indicates a broad interest in AI applications. The explicit mention of targeting AI/ML/Data Science internship roles aligns well with a growth-oriented and technically focused culture.
Soft Skills & Operational Fit
The candidate demonstrates strong problem-solving skills through complex project implementations like the DeepDiabetic and Personal AI Assistant. The modular Python architecture in the AI assistant project suggests an understanding of maintainability and scalability. The focus on offline execution and low-latency inference indicates an appreciation for practical system constraints and optimization.