Skip to content
View sravanni369's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report sravanni369

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sravanni369/README.md

banner

Hi, I'm Sravani πŸ‘‹

AI/ML Data Engineer @ MEEAMI Technologies β€” Python, SQL & PyTorch; RAG/LLM systems, built in public one commit at a time.

Email LinkedIn Portfolio


πŸš€ What I'm about

  • πŸ’Ό AI/ML Data Engineer at MEEAMI Technologies β€” LLMs, RAG & conversational AI
  • πŸ”­ I ship small, runnable, documented projects β€” real code with real logs, no vaporware
  • πŸ“… One Python exercise every day in python-daily β€” data pipelines, ML patterns, LLM building blocks
  • 🧠 Currently deep in PyTorch β€” latest: a neural network that scores 98/100 on the FizzBuzz interview
  • πŸ“Š Day job muscle: SQL, data quality, and testing β€” I find the row that breaks the report
  • πŸŽ“ Indiana Wesleyan University Β· certifications from Microsoft, Google Cloud, MathWorks & Coursera below

πŸ› οΈ Tech stack

Python PyTorch scikit-learn pandas NumPy LangChain OpenCV

Oracle SQL SQL Server SQLite Excel

Git Jupyter VS Code JIRA

πŸ“Œ Featured projects

Project What it proves
🧠 neural-fizzbuzz PyTorch MLP learns FizzBuzz from raw binary digits β€” 98/100 on unseen numbers, full training log + VS Code run screenshots included
πŸ“… python-daily Consistency: one focused, runnable Python exercise per day β€” data quality, sqlite3, log parsing, embeddings, PyTorch drills
πŸ“± sms-spam-detection Classic ML done properly: TF-IDF + Random Forest spam classifier on the UCI SMS corpus
πŸ“„ plagiarism-checker TF-IDF + cosine similarity from scratch β€” the math behind "how similar are these documents?"
πŸ€– rag-conversational-ai RAG pipeline learning build: LangChain + LlamaIndex, FAISS vector search, Dockerized services
πŸ‘οΈ eye-contour-tracking-sam2 SAM2 segmentation experiment for eye-contour annotation (PyTorch + OpenCV)
πŸ” bm25-search Zero-dependency BM25 full-text search engine in pure Python β€” inverted index, Lucene-style IDF, CLI, 30 pytest tests, CI on Python 3.9–3.12
πŸ—£οΈ pdf-image-ocr-reader OCR for PDFs and scans (Tesseract + PyMuPDF) with offline text-to-speech for accessibility

πŸ“œ Certifications

Certification Issuer Issued
Annotate and Analyze Objects for Vision Coursera Mar 2026
Introduction to Generative AI for Developers with Copilot Microsoft Feb 2026
Introduction to Image Processing MathWorks Feb 2026
Model Training & Evaluation Coursera Feb 2026
NVIDIA: Fundamentals of Machine Learning Whizlabs Feb 2026
Python Programming Fundamentals Microsoft Feb 2026
Introduction to SQL for BigQuery and Cloud SQL Google Cloud Jun 2025

Credential IDs are listed on my LinkedIn.

πŸ“ˆ GitHub stats

GitHub streak

Contribution activity graph


πŸ“§ sravannicareerv@gmail.com Β· LinkedIn Β· Portfolio

Pinned Loading

  1. eye-contour-tracking-sam2 eye-contour-tracking-sam2 Public

    SAM2 segmentation experiment for eye-contour annotation (PyTorch, OpenCV)

  2. python-daily python-daily Public

    One focused Python exercise every day - data engineering, ML, and LLM patterns

    Python

  3. rag-conversational-ai rag-conversational-ai Public

    RAG pipeline learning project: LangChain + LlamaIndex, FAISS vector search, Dockerized microservices

  4. sms-spam-detection sms-spam-detection Public

    SMS spam classifier using TF-IDF + Random Forest (~98% F1 on UCI SMS Spam Collection)

    Python

  5. bm25-search bm25-search Public

    A zero-dependency, fully-typed Okapi BM25 full-text search engine for Python β€” inverted index, correct BM25 ranking, JSON persistence, and a CLI.

    Python

  6. neural-fizzbuzz neural-fizzbuzz Public

    A PyTorch neural network takes the FizzBuzz interview β€” trained on binary digits of 101-1023, scores 98/100 on unseen numbers 1-100

    Python