Skip to content

Amith Vardhan Reddy Surasani

Data Scientist • Hyderabad, Telangana, India • a**************@gmail.com • +91*******399 • github.com/••••• • drivetube.ai/•••••

Professional Summary

Data Scientist with 2 years of experience building multilingual NLP pipelines, recommendation systems, and generative-AI user experiences. Proficient in Python-based data engineering and ML workflows using scikit-learn and TensorFlow, with hands-on experience fine-tuning LLMs such as Llama 3 and integrating GPT-4o-mini for context-aware responses. Delivered a news-aggregation and processing pipeline that ingested 10,000+ articles and a personalization engine serving 9,800+ users; implemented semantic retrieval using SentenceTransformers and vector databases to enable RAG-driven responses. Built production-ready APIs with FastAPI and user interfaces with React, and automated meeting transcription and summarization using CrewAI agents and OpenAI Whisper. Experienced across news/consumer content, meeting automation, fraud modeling, and medical imaging, taking end-to-end ownership from data ingestion to deployed model inference.

Technical Skills

Programming Language: Python
Frontend Technologies: React
Backend Technologies: FastAPI,Gmail API
Databases: MongoDB,MySQL
Version Control & Development Tools: Jupyter Notebook
Testing & QA: Selenium
Data Analysis & Visualization: NumPy,Pandas,GPT-4o-mini
Machine Learning & AI: Convolutional Neural Networks,CNN
AI/ML Frameworks & Libraries: scikit-learn,TensorFlow,BeautifulSoup
Generative AI & LLMs: Llama 3,OpenAI,Whisper,CrewAI,Groq
Vector Databases & RAG: Vector Databases
Identity & Access Management (IAM): OAuth 2.0

Work Experience

DUTA
Remote
Data Scientist
Mar 2024 – Mar 2026
Worked on multilingual news aggregation, content processing, personalization, and an AI chatbot; supported ingestion, model training, retrieval, and production APIs for a consumer news service.
Tech Stack: Python, BeautifulSoup, Selenium, Llama 3, Groq API, GPT-4o-mini, scikit-learn, FastAPI, React, SentenceTransformers
  • Engineered a multilingual news aggregation pipeline using BeautifulSoup and Selenium to scrape English, Telugu, and Hindi sites, extracting and processing 10,000+ articles across multiple categories.
  • Developed content-processing workflows leveraging Llama 3 and the Groq API to generate article summaries and cross-language translations; fine-tuned models on curated article datasets to improve relevance.
  • Built a personalized recommendation engine in Python with collaborative and content-based filtering implemented via scikit-learn, delivering tailored suggestions to 9,800+ users.
  • Designed and deployed a FastAPI backend integrated with GPT-4o-mini to provide context-aware chatbot responses, adding conversational memory and session logging for continuity.
  • Implemented semantic retrieval using SentenceTransformers and cosine-similarity with a vector database to enable retrieval-augmented generation and automated evaluation of response quality.
  • Integrated Newsdata.io and Inshorts APIs to automate article ingestion and metadata normalization, ensuring daily content freshness and consistent category mapping.
  • Delivered a React-based front end for the chatbot enabling real-time interactions and session persistence for user-facing conversations.

Projects

Minutes of Meeting Generation and Email Drafting
Tools Used: CrewAI, OpenAI Whisper, Gmail API, OAuth 2.0, MongoDB
  • Architected an agentic meeting-minutes automation pipeline using CrewAI agents and custom flows to orchestrate transcription, summarization, and action-item extraction.
  • Implemented end-to-end transcription and summarization using OpenAI Whisper and multi-agent orchestration to convert meeting audio into concise summaries and sentiment signals.
  • Integrated Gmail API with OAuth 2.0 to automate generation and delivery of meeting-minute drafts to attendees.
  • Persisted transcripts and metadata to MongoDB to enable retrieval, incremental summarization, and semantic search for follow-up workflows.
Credit Card Fraud Detection Using Transactions Data
Tools Used: Python, Pandas, NumPy, MySQL, scikit-learn, Logistic Regression, LDA, Gaussian Naive Bayes
  • Performed exploratory data analysis and preprocessing on the European cardholders transaction dataset using Python and Pandas to identify feature distributions and outliers.
  • Exported cleaned datasets to MySQL and implemented feature scaling to prepare data for modeling and reproducibility.
  • Trained and evaluated Logistic Regression, Linear Discriminant Analysis, and Gaussian Naive Bayes models using scikit-learn, comparing accuracy, precision, recall, and F1-score.
  • Achieved 95.37% classification accuracy with Logistic Regression after iterative feature selection and model calibration, and compared model trade-offs to select the production candidate.
Brain Tumor Detection Using Convolutional Neural Network
Tools Used: TensorFlow, Convolutional Neural Networks CNN, NumPy
  • Developed a CNN-based classifier in TensorFlow to detect brain tumors from MRI images, implementing image preprocessing and normalization to improve training stability.
  • Tuned hyperparameters including learning rate, batch size, and epochs and adjusted the train-test split, improving validation accuracy from ~45–60% to approximately 75%.
  • Evaluated model performance using classification metrics and prepared model artifacts for further experimentation and potential deployment.

Education

Wilmington University
Master of Science in Information Systems Technologies (Information Assurance concentration) • New Castle, Delaware, United States • Aug 2022 – Dec 2023
Coursework: Data Management, Cloud Management
MVSR Engineering College - Osmania University
Bachelor of Engineering in Electronics and Communication Engineering • Hyderabad, Telangana, India • Aug 2017 – Sep 2021
Coursework: Digital Image Processing

Certifications

Google Advanced Data Analytics — Google
Google Data Analytics — Google
DeepLearning.Al TensorFlow Developer — DeepLearning.AI
Complete Machine Learning & Data Science Bootcamp 2023 — Udemy
Data Science Course: Complete Data Science Bootcamp — Udemy
IBM Data Science — IBM
IBM Data Analyst — IBM

Achievements

  • Top 50 - IEEE Computer Society Programming League — 2020
  • Top 50 - MVSR Programming League — 2020
  • 2nd Verbal Mention Award - MVSR MUN

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

Everything on Drivetube

Six products, two of them free forever. Start wherever you are.

Read the docs →
  • 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
  • Verified jobs, posted in the last 3 days

    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 ProgramFrom $199.99

    We run your job hunt for you

    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
  • Written by senior career writers

    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 MembershipFrom $49.99/yr

    AI tools, gated filters and a $10,000+ library

    from $49.99/year (₹1,999/year in India), or $4.99/month in the iOS app. 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
  • For employers — no job postings, no applications

    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
  • Documentation

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

  • Playbooks

    tactical job-search guides. Each post is one named tactic with the situation it applies to, the exact steps, a copy-paste message and honest failure modes. Free, no account.

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

Pricing is identical on the web, iOS and Android — no app-store markup. Monthly Community membership is purchased in the iOS app only; the website sells annual plans. The Android app has no in-app purchase, so Android members subscribe on drivetube.ai and then sign in to the app with full access. Membership follows your account, not your device.