Block or report smithparekh
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.
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuse
AI Engineer at ParityCube with 4 years of experience designing and shipping production-grade AI systems. I build systems that reason, plan, and act — not just chat.
- Shipped a self-learning RAG classifier (Qdrant + OpenAI embeddings) currently in production
- Built MetabaseQueryBot — an autonomous LangGraph agent achieving 80% data validation accuracy
- Deployed an AWS Fraud Detector ML pipeline that reduced fraud by 80% and manual review by 90%
- Built an MCP server enabling plain-English access to campaign data — zero SQL required
- 6.8M+ transactions processed through my data pipelines daily
AI and LLM
Data and Analytics
| Project | Description | Stack |
|---|---|---|
| Resume ATS Agent | Multi-agent system — 4 CrewAI agents rewrite and score resumes for ATS | CrewAI, GPT-4o-mini, Streamlit |
| Medicare AI Assistant | RAG chatbot for medical PDFs using vector search | LangChain, FAISS, Streamlit |
| Resume AI Analyzer | AI resume analyzer with instant structured feedback | Groq, LLaMA-3.3-70b, Streamlit |
| Retail Data Pipeline | End-to-end pipeline: S3 to Snowflake to Power BI | Python, Snowflake, Power BI |
Open to AI Engineer, Data Analyst, and ML Engineer roles at MNCs in Mumbai.
Popular repositories Loading
-
-
Diabetes-Crisp-metrics-task Diabetes-Crisp-metrics-task Public
Diabetes prediction using machine learning classification — logistic regression and model evaluation
Jupyter Notebook 1
-
Credit_card_fraud_detection_Crisp_metrics_task Credit_card_fraud_detection_Crisp_metrics_task Public
Credit card fraud detection using machine learning — classification models and performance evaluation
Jupyter Notebook 1
-
Retail-Analysis Retail-Analysis Public
End-to-end retail data pipeline: Amazon S3 to Snowflake (AUTO_INGEST) to Power BI — FMCG campaign analytics
Jupyter Notebook 1
-
MLForEveryday MLForEveryday Public
Practical machine learning notebooks — regression, classification and data analysis with scikit-learn
Jupyter Notebook 1
-
If the problem persists, check the GitHub status page or contact support.