Skip to content
View The-Name-is-Karthik's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report The-Name-is-Karthik

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

Karthik Kalikivayi

GenAI Engineer · Agentic AI · RAG · Applied ML


About Me

I’m a 2024 graduate from IIT Kanpur with a background in Physics, currently focused on building production-grade AI systems across:

  • Generative AI
  • Agentic workflows
  • Retrieval-Augmented Generation (RAG)
  • Applied Machine Learning
  • Backend APIs and deployment

I like working on problems where the challenge is not just model performance, but how the whole system behaves end to end reliability, control flow, retrieval quality, deployment, and observability.


Tech Stack

Core

GenAI / NLP / ML


What I Build

Agentic AI Systems

  • LangGraph-based workflows
  • Tool use and control flow
  • Reliability and failure handling
  • Structured reasoning pipelines

RAG Applications

  • Multi-source ingestion
  • Embedding pipelines
  • Retrieval grounding
  • Citation-backed responses

Applied ML Systems

  • Imbalanced classification
  • Explainable ML pipelines
  • Evaluation and optimization
  • Production-oriented modeling

Backend + Deployment

  • FastAPI services
  • Dockerized workflows
  • AWS deployment
  • End-to-end AI infrastructure
---

Featured Projects

Autonomous AML Intelligence System

Production-style AML investigation system combining classical ML with LLM-based agentic reasoning.

What it does

  • Detects suspicious patterns in financial transactions
  • Uses LLM agents to investigate flagged cases
  • Generates audit-ready reports for review workflows
  • Adds privacy and explainability layers for safer deployment

Key highlights

  • Built on 9.5M+ transaction records
  • Used CatBoost for highly imbalanced fraud detection
  • Designed LangGraph workflows for evidence gathering and report generation
  • Deployed with FastAPI, Docker, and AWS
  • Added SHAP for model explainability

Tech: Python CatBoost LangGraph Llama FastAPI Docker AWS SHAP


Multi-Source RAG Engine

A retrieval system that lets users query information across PDFs, web pages, DOCX files, and YouTube transcripts.

What it does

  • Ingests multiple unstructured data formats
  • Creates semantic retrieval pipelines using embeddings
  • Returns grounded answers with citations
  • Supports conversational querying through a UI

Key highlights

  • Built with Sentence-Transformers + ChromaDB
  • Used LangChain and Gemini
  • Reduced hallucinations using retrieval grounding
  • Added conversational memory and interactive querying

Tech: Python LangChain Gemini Sentence-Transformers ChromaDB Streamlit


Autonomous Code Debugging Agent

A closed-loop LLM-powered debugging workflow that detects, patches, and validates Python code issues.

What it does

  • Runs buggy code in a controlled environment
  • Detects syntax, runtime, and logic errors
  • Generates patches automatically
  • Re-validates code after fixes

Key highlights

  • Designed a loop: Execute → Parse → Patch → Validate
  • Added sandboxed execution for reproducibility
  • Built a debugging UI with logs and diff visualization

Tech: Python Gemini Docker Streamlit Agentic Workflows


Achievements

  • Top 10 Finalist SARCathon, PAN-IIT AI Hackathon, IIT Bombay
  • Built a multilingual RAG-based FAQ system under time-constrained hackathon settings
  • Interested in building AI systems that balance speed, reliability, and practical utility

Current Focus

  • Reliable agentic AI systems
  • Better retrieval quality for RAG
  • Production-ready LLM application design
  • AI systems that are observable, controllable, and deployable

GitHub Analytics


Connect With Me


Open to opportunities in

Generative AI · Applied ML · NLP · LLM Engineering · AI Backend Systems

Pinned Loading

  1. AML-Intelligence-Autonomous-Financial-Surveillance AML-Intelligence-Autonomous-Financial-Surveillance Public

    An autonomous AML surveillance system that cut manual fraud review time by 70% — applying CatBoost ensemble learning and LangGraph agents to detect 28+ money laundering typologies at 92% precision …

    Python

  2. Autonomous-Code-Debugging-Agent-ACDA- Autonomous-Code-Debugging-Agent-ACDA- Public

    A closed-loop agentic debugging system (Execute → Parse → Generate → Patch → Validate) using Google Gemini + Docker sandboxing, achieving 90%+ fix rate on Python errors with 100% reproducibility an…

    Python

  3. Multi-Source-RAG-Engine Multi-Source-RAG-Engine Public

    This project is a sophisticated Retrieval-Augmented Generation (RAG) application that transforms static content into a dynamic conversational partner. It leverages the power of Google's Gemini mode…

    Python

  4. AI-Powered-Multilingual-FAQ-System- AI-Powered-Multilingual-FAQ-System- Public

    A multilingual FAQ system using Sentence-Transformers + Pinecone semantic retrieval outperforming keyword-based baselines on low-latency, high-concurrency benchmarks.

    CSS 1

  5. Financial-Document-Analyser-System-Using-CrewAI- Financial-Document-Analyser-System-Using-CrewAI- Public

    An intelligent, multi-agent financial analysis system built with FastAPI, CrewAI, and Celery. This platform transforms raw financial PDFs into professional investment reports through a specialized …

    Python

  6. Scouts_Leadsets_Micro_Module Scouts_Leadsets_Micro_Module Public

    This project is a micro-module for the Scout application, designed to manage leadsets, trigger searches via Exa, enrich contact data, and export results. UI Screenshot

    JavaScript