Skip to content
View rishikesh-20's full-sized avatar

Highlights

  • Pro

Block or report rishikesh-20

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
rishikesh-20/README.md

💫 About Me:

Computer Science graduate student at UNC Charlotte with a focus on data engineering, machine learning, and scalable AI-driven systems. Experience working with Python, SQL, Snowflake, Apache Airflow, Airbyte, dbt, DuckDB, AWS, and analytics tools to design, maintain, and optimize ETL/ELT pipelines, cloud data warehouses, and reporting workflows. Background includes data ingestion, transformation, validation, orchestration, data modeling, feature engineering, and dashboard reporting systems used by HR, management, and client teams. Familiar with modern data stack technologies, workflow automation, data quality monitoring, vector databases, retrieval-augmented generation (RAG), LLM pipelines, prompt engineering, embeddings, and building data infrastructure for AI and machine learning applications. Strong interest in MLOps, generative AI, predictive modeling, AI infrastructure, and developing scalable machine learning and LLM-powered solutions for real-world business problems.

🌐 Socials:

LinkedIn

💻 Tech Stack:

C++ Python Java HTML5 AWS Vercel Apache Spark Snowflake Apache Airflow MongoDB Postgres MySQL Matplotlib NumPy Pandas scikit-learn mlflow GitHub Git Power Bi

📊 GitHub Stats:



Pinned Loading

  1. SEC-Filing-Intelligence SEC-Filing-Intelligence Public

    End-to-end Databricks lakehouse turning SEC EDGAR filings into financial KPIs and ML insights - Bronze-->Silver-->Gold medallion in declarative SQL, XGBoost predictions, and an interactive dashboard.

    Python

  2. llm-prompt-benchmark llm-prompt-benchmark Public

    LLM prompt benchmark on 150 RAGBench samples × 5 strategies. RAG: 89.5% faithfulness, 10.5% ungrounded vs zero-shot: 31.3%, 68.7%. Qwen3 + Gemini judge.

    Python

  3. braindrain braindrain Public

    Interactive Streamlit dashboard covering all 50 U.S. states with 5 analysis modules, 7 ACS 5-year Census tables, 10+ migration/talent/affordability metrics, and 2 AI workflows for chart explanation…

    Python

  4. resumeforgeAI resumeforgeAI Public

    Python