Skip to content

KANDERI BABU TRISHA

Machine Learning Engineer (Entry-level) • Tirupati, Andhra Pradesh • k************@gmail.com • +91*******357 • github.com/••••• • drivetube.ai/•••••

Professional Summary

Machine Learning Engineer with 0 years of experience building and deploying ML models and full-stack prototypes using Python, TensorFlow/Keras, Flask, and SQL. Hands-on experience with transfer learning for image classification, time-series forecasting (ARIMA, LSTM, XGBoost), feature engineering, and delivering Flask/FastAPI backends and dashboards for real-time inference and monitoring. Strong fundamentals in data structures, OOP, and databases; seeking entry-level ML/AI roles where I can contribute to production-ready model pipelines and data-driven products.

Technical Skills

Programming Languages: Python,C,JavaScript
Web Technologies: REST APIs,HTML,CSS
Frameworks and Libraries: TensorFlow,Keras,Scikit-learn,Pandas,NumPy,Flask,FastAPI,Tailwind CSS,Chart.js
Databases: SQL
Cloud and DevOps: Azure
Data and Analytics: XGBoost,LSTM,ARIMA,Convolutional Neural Networks,Transfer Learning,VGG16,ResNet50,Data Visualization,Power BI
Tools and Methodologies: GitHub,VS Code,Google Colab,Text-to-Speech multilingual
Core Concepts: Data Structures & Algorithms,Object-Oriented Programming,DBMS,Machine Learning Fundamentals,Computer Networks

Work Experience

Smart Bridge
Tirupati, Andhra Pradesh
AI/ML Intern
May 2025 – Jul 2025
Built an image-based disease classification solution; worked on model training, evaluation, and Flask deployment to deliver real-time predictions for poultry disease detection.
Tech Stack: Python, TensorFlow, Keras, VGG16, Flask, Pandas, NumPy, Google Colab
  • Designed and trained a transfer-learning image classifier using VGG16 as backbone to detect four poultry disease classes; selected architecture based on dataset characteristics and accuracy requirements.
  • Preprocessed input images to 224×224×3, froze base layers initially and implemented selective unfreezing to preserve pretrained features while enabling task-specific learning.
  • Fine-tuned the final 4 layers of VGG16 which improved validation accuracy from 95.40% to 96.25%, demonstrating better generalization on held-out data.
  • Managed end-to-end model lifecycle: data preprocessing, training loops, evaluation metrics and iterative hyperparameter tuning using TensorFlow/Keras and Google Colab.
  • Packaged the trained model behind a Flask REST API to enable real-time single-image inference from uploads; validated inference flow and integrated with a simple UI for tester usage.
  • Prepared evaluation reports and model artifacts for handover, including confusion matrices and per-class accuracy to support deployment decisions and future dataset expansion.
Infosys Springboard
Tirupati, Andhra Pradesh
AI Intern
Aug 2025 – Oct 2025
Worked on demand forecasting and capacity optimization for Azure compute/storage using time-series and ML models; built feature pipelines and dashboards integrated with Flask backends.
Tech Stack: Python, Scikit-learn, XGBoost, ARIMA, LSTM, Flask, Pandas, Chart.js, Azure
  • Developed and benchmarked time-series and supervised models (ARIMA, LSTM, XGBoost) to forecast Azure resource demand across 4 regions and 3 resource types, comparing accuracy and runtime tradeoffs.
  • Engineered feature pipelines from three months (1,080 records) of historical utilization data, merging usage with external indicators to improve predictive signal and model robustness.
  • Achieved baseline forecasting MAPE of 8–12% using ARIMA and LSTM models on regional resource series, enabling more reliable short-term capacity planning.
  • Built and evaluated XGBoost models that reduced backtesting error considerably on the available dataset; documented model selection rationale and validation procedure.
  • Implemented Flask backend endpoints and interactive dashboards (dynamic filters by region, resource type, and date) to expose forecasts and visualizations for stakeholders.
  • Performed exploratory data analysis and visualization to identify seasonality, trends, and anomalies, informing feature engineering and model retraining cadence.

Projects

Transfer Learning-Based Poultry Disease Classification
Tools Used: Python, TensorFlow, Keras, CNN, VGG16, ResNet50, Flask, Google Colab
  • Built a deep learning classifier to detect four poultry disease classes (Salmonella, Newcastle Disease, Coccidiosis, Healthy) using transfer learning and CNN backbones.
  • Fine-tuned a VGG16 model by unfreezing final layers and tuning learning rates to obtain 97.85% training accuracy and 96.25% validation accuracy on an 80/20 split.
  • Preprocessed images to uniform 224×224×3 tensors and applied training practices (freezing/unfreezing) to balance pretrained feature reuse with task-specific learning.
  • Integrated the trained model into a Flask web application to accept image uploads and return real-time predictions for end-user testing and demo purposes.
Azure Demand Forecasting & Capacity Optimization System
Tools Used: Python, Flask, Scikit-learn, Pandas, ARIMA, XGBoost, LSTM, HTML, Tailwind CSS, Chart.js
  • Built and compared ARIMA, XGBoost, and LSTM models to forecast compute and storage demand across multiple regions and resource types using 3 months of historical usage.
  • Achieved forecast MAPE of 8–12% with ARIMA/LSTM baselines; used XGBoost for additional experiments that produced lower backtesting error on this dataset.
  • Performed EDA on merged usage and external factors (economic index, market demand signals, holiday indicators) to derive predictive features and lag variables.
  • Developed Flask APIs and an interactive dashboard with dynamic filtering to visualize forecasts and support capacity decision-making by region/resource/date.
AgroAdvisor: AI-Driven Plant Disease Detection & Crop Advisory
Tools Used: Python, TensorFlow, Keras, FastAPI, HTML, CSS, JavaScript, Text-to-Speech
  • Built an image-based plant disease classifier covering 38 disease classes across 14 crops, achieving ~92% validation accuracy using CNN approaches.
  • Implemented a FastAPI backend serving real-time predictions and returning treatment/cure suggestions from a curated disease knowledge base.
  • Curated a structured knowledge base mapping each disease class to recommended treatments and precautions for instant retrieval alongside predictions.
  • Added multilingual (English + Telugu) text-to-speech output to deliver accessible cure recommendations to farmers with limited literacy.

Education

Sri Venkateswara College of Engineering (SVCE), Tirupati
B.Tech, Computer Science (AI & ML) • Tirupati, Andhra Pradesh • 2022 – 2026
Narayana Junior College, Tirupati
Intermediate • Tirupati, Andhra Pradesh • 2020 – 2022
Red Cherries School, Tirupati
SSC • Tirupati, Andhra Pradesh • 2020

Certifications

AI Fundamentals — IBM
Cloud Foundations — AWS
Analyzing Data with R — IBM (edX)

Powered by Drivetube · Create your own profile at drivetube.ai

Explore Drivetube

  • Drivetube Profile — your free digital resume — at drivetube.ai/in/your-name: one true standard resume with a Hiring Snapshot (visa status, expected salary, notice period, work preference, relocation), an ATS-ready PDF download and a single shareable link. Free forever; interview requests come from verified employers and your contact details stay masked until you accept. Documentation.
  • Free Job Board — verified openings crawled ATS-by-ATS from 100,000+ real company career pages across 35 ATS platforms. Shows the true posting date from the source ATS — not when a listing was indexed — and deletes every general listing 3 days after it was actually posted. No ghost jobs, no ad-sponsored listings, no staffing reposts, no account needed. Documentation.
  • Job Hunt Program — managed job hunting, a one-time purchase from $199.99. JobScout matches verified roles to your real experience band, Blend AI writes a uniquely tailored resume and cover letter for every application, and the Autofill extension fills the form — or Let Us Apply submits it for you. Documentation.
  • Resume Writing Services — human-written, ATS-optimised resumes by senior career writers, from ₹499.99 / $25.99. Available in every country, written to the destination country's own standard — a US resume, UK CV, German Lebenslauf and Indian resume are genuinely different documents. A paid service, separate from the free Drivetube Profile. Documentation.
  • Community Membership — from $4.99/month (₹1,999/year in India). Unlocks the gated job-board filters — visa sponsorship, security clearance, workplace and application time — plus Job-Scout AI matching, Resume Report AI, Interview AI prep sheets, Recruiter Outreach AI sent from your own Gmail, Apply or Skip triage, a daily market feed and a $10,000+ library including 23 ATS-validated resume templates. Documentation.
  • Drivetube Hire — for employers — hiring with no job postings and no applications. Paste your real job description and AI matches it against candidates' true standard resumes, returning ranked candidates with a match %, matched and missing skills and written reasoning. Free tier included; employers pay, candidates never do. Documentation.

Full product documentation — every product explained, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.

The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.