Vinod Kumar Yerraballi
Professional Summary
AI/ML Analyst with an M.Sc. in Applied Mathematics & Statistics, specialising in predictive modelling, NLP, feature engineering and model validation on large datasets. Delivered a 25% accuracy lift on an NLP text-classification pipeline, cut diabetes-model false negatives 43% (508 to 289) using SMOTE and threshold tuning, and shipped 5+ supervised and unsupervised models at 90% average accuracy. Currently safeguard data quality for production AI pipelines (Python, Scrapy) at Rubick.AI. Pairs rigorous statistical analysis (hypothesis testing, A/B testing) with Power BI storytelling to turn model output into decisions stakeholders act on.
Technical Skills
Work Experience
- Cleaned and transformed 1,000+ customer feedback records using Python and Pandas, resolving inconsistencies and structuring unstructured text to prepare data for modeling.
- Performed exploratory data analysis and feature engineering on feedback text, extracting signal for sentiment and topic classification and producing candidate features for model training.
- Built and validated a text classification pipeline using scikit-learn (feature extraction, model training, evaluation) and assessed performance with accuracy, precision and recall to ensure alignment with stakeholder requirements.
- Developed 3+ interactive Streamlit dashboards that translated model outputs into visual summaries and class distributions for non-technical stakeholders, enabling faster data-driven decisions.
- Documented preprocessing, feature selection and validation steps in reproducible Jupyter notebooks to ensure handover and repeatable experiments for the analytics team.
- Collaborated with business stakeholders to define annotation guidelines and label schema, improving label consistency and enabling more reliable supervised model training.
- Executed 5 supervised and unsupervised ML tasks (regression, classification, clustering) end-to-end, achieving an average model accuracy of ~90% across defined problem statements.
- Conducted structured EDA and hypothesis testing prior to modeling to improve data readiness and reduce iterative rework during validation phases.
- Applied iterative feature engineering and hyperparameter tuning using scikit-learn and XGBoost, improving baseline model performance by up to 40%.
- Validated models using appropriate metrics (R² for regression, confusion matrix and accuracy for classification) and applied cross-validation to ensure generalization.
- Authored 5+ technical write-ups documenting methodology, code and results for non-technical audiences; combined posts reached 500+ views demonstrating clear communication of findings.
- Maintained reproducibility using Git and Jupyter Notebooks and participated in Jira-based workflows to track tasks and deliverables.
Projects
- I developed an end-to-end Python automation pipeline using Playwright (Chromium) that scans Naukri for up to eight role-location combinations per run. It filters listings posted within the last 24 hours, ensuring that applications are submitted for fresh openings.
- I designed a weighted job-matching engine that scores each listing against my profile based on five criteria: skills, experience, location, education, and preferences. This engine utilises Naukri’s key-skills list along with skills extracted from the full job description, filtering out low-fit jobs based on a configurable minimum score.
- Additionally, I integrated three LLM providers (Gemini, Ollama running locally with Qwen3 8B, and Anthropic Claude) with an automatic fallback mechanism. This setup generates job-specific DOCX resume drafts by parsing PDF resumes with PyPDF and building drafts using python-docx.
Education
Achievements
- Ranked top 5% in Analytics Vidhya Data Science Contest: Placed in the top 5% among 10,000+ participants by applying structured feature engineering and effective model design.
- Model improvement through experimentation: Improved model accuracy by up to 40% over baseline through systematic experimentation and hyperparameter tuning across projects.
Powered by Drivetube · Create your own profile at drivetube.ai
Everything on Drivetube
Six products, two of them free forever. Start wherever you are.
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 BoardFree
Verified jobs, posted in the last 3 days
verified openings crawled ATS-by-ATS from 160,000+ real company career pages across 50+ 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 - Resume Writing ServicesFrom $25.99
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 - Drivetube OneFrom $39.99 / 3 mo
Daily matched jobs, tailored resumes, or we apply for you
Drivetube's paid service. Community sends daily Jobsheets of fresh jobs matched to your profile on WhatsApp and email, with the Drivetube Community ($39.99 for 3 months or $69.99 for 6 months; ₹999 or ₹1,899 in India). Jobhunt is one-time application credits with Community included: one credit tailors one resume and its cover letter (100 for $99 with 3 months of Community, 250 for $199 with 6 months). Let Us Apply is an add-on to Jobhunt: a human expert applies 250 times for you on your credits ($0.60 each, $150). Everything lives on one dashboard at drivetube.ai/drivetubeone.
Documentation - Drivetube HireFree tier
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.