Skip to content
View Mohith-akash's full-sized avatar
1 follower · 0 following

Block or report Mohith-akash

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
Mohith-akash/README.md

👋 Mohith Akash

Data Engineer & AI Developer

LinkedIn Email


Building Production Data Platforms & Agentic AI Systems

4 Live Projects • 13M+ Records Processed • $0 Infrastructure Cost

🚀 Featured Projects

📦 Vortex: Revenue Recovery Engine

Live Demo Code

Real-time streaming platform for AI-powered cart recovery

Feature Details
⚡ Real-time Streaming: Azure Event Hub → <500ms
🧠 Agentic AI: Cerebras Llama 3.1 + 5 customer archetypes
🏅 Delta Live Tables: Bronze → Silver → Gold
🔍 Semantic Search: Voyage AI embeddings
📊 A/B Testing: z-score with 95% confidence intervals

Databricks Azure Event Hub Delta Live Tables
Cerebras Voyage AI dbt Core Streamlit

🌐 Global News Intelligence

Live Demo Code

Hybrid RAG system for querying 13M+ news events

Feature Details
📊 13M+ events from GDELT + GKG feeds
🔄 100K+ daily events with 15-min refresh
🤖 Dual AI: Vector Search + Text-to-SQL agents
🧠 GKG Emotions: 2.2K+ dimensions analyzed
⚡ Polars: 10x faster than Pandas
✅ Great Expectations data quality checks
💰 $0/month serverless on MotherDuck

Python Polars dbt MotherDuck
Dagster Voyage AI LlamaIndex Cerebras

🛒 Olist E-Commerce Analytics

Live Demo Code

End-to-end Databricks Lakehouse for e-commerce analytics

Feature Details
🏗️ Medallion Architecture: Bronze → Silver → Gold
📦 100K+ orders processed with Delta Lake
⭐ Kimball Star Schema: 7 dimension + 1 fact tables
🔐 Unity Catalog: Row-level governance
📊 Power BI: Interactive dashboards

Databricks Delta Lake SQL
Power BI Unity Catalog Streamlit

✉️ AI Cover Letter Generator

Code

Multi-LLM orchestration for personalized job applications

Feature Details
🏆 Auto CV Selection: 4 types + 10 similar roles
🔍 Company Research: Tavily API, positives-only
🧠 LLM Generation: Cerebras Llama 3.1
🎯 90+ Tool Mappings: Dagster ↔ Airflow
📊 A-F Quality Score: Professionalism checks
🌍 Global: Any country, auto-translates

Python Streamlit Cerebras
Voyage AI Tavily Jina Reader

🛠️ Tech Stack

Python SQL Databricks Azure Delta Lake
ETL/ELT dbt Polars Dagster Great Expectations
MotherDuck DuckDB
Generative AI RAG NLP LlamaIndex Voyage AI Cerebras
Tavily Jina Reader
Streamlit Power BI GitHub Actions

📈 What I Build

┌─────────────────────────────────────────────────────────────────────────┐
│  ⚡ Real-time Streaming   →  Azure Event Hub, Delta Live Tables        │
│  🧱 Lakehouse Architecture → Databricks, Delta Lake, Medallion         │
│  🔄 ETL/ELT Pipelines      →  Polars, Dagster, dbt Core                │
│  🦆 Cloud Data Warehouses  →  MotherDuck, DuckDB, serverless SQL       │
│  🤖 Agentic AI Systems     →  LLM agents, RAG, Text-to-SQL             │
│  🚀 Vector Search          →  Voyage AI embeddings, semantic search    │
│  🔌 API Orchestration      →  Multi-API integration, Tavily, Jina      │
│  📊 Interactive Dashboards →  Streamlit, Power BI, Plotly              │
│  🔄 CI/CD Automation       →  GitHub Actions, scheduled pipelines      │
└─────────────────────────────────────────────────────────────────────────┘

🎓 Certifications

Google Advanced Data Analytics
Google Cybersecurity
AI for Data Professionals

💼 Open to Opportunities

Data Engineer · AI Engineer · Analytics Engineer · Data Analyst

Ready to relocate internationally

Pinned Loading

  1. Global-News-Intel-Platform Global-News-Intel-Platform Public

    AI-powered geopolitical news intelligence platform. Ingests 100K+ daily events from GDELT, stores in MotherDuck (DuckDB), orchestrates with Dagster, and features an AI chat interface with Text-to-S…

    Python 4

  2. olist-analytics-platform olist-analytics-platform Public

    End-to-end analytics platform: CSV → Databricks → Delta Lake → Streamlit Dashboard | 100K+ Brazilian e-commerce orders

    Python

  3. Excel-Data-Analyst-Portfolio-Project Excel-Data-Analyst-Portfolio-Project Public

    An interactive Excel dashboard analyzing 13k+ data analyst job postings