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

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Block or report kartikeyamandhar

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
kartikeyamandhar/README.md

Kartikeya Mandhar

UCLA Anderson MSBA '26

LinkedIn Email

What I Ship

Project Stack What It Does
MAIRS LangGraph, Neo4j, Pinecone, BGE Reranker, DistilBERT, FastAPI Multi-agent investment research system with sentiment analysis and graph-augmented retrieval
Flade KG-RAG Neo4j, LlamaIndex, FastAPI, React Knowledge graph RAG system — sub-3-min processing, sub-2-sec query latency, hybrid retrieval across 4 methods
Neo4j GraphRAG for Hamilton Apache Hamilton, Neo4j, Python OSS contribution: 4-module pipeline (ingest → embed → retrieve → generate), 40 test queries, PR-ready
Dynamic Pricing Analytics Python, SQL, Ensemble ML Forecasting model on 693K records, 20+ engineered features, RMSE: $1.42
CSV Analytics Portal Django REST, NLP Query Engine, Anomaly Detection Full analytics platform with dashboards, ML anomaly detection, and natural language querying
Ranking Benchmark BM25, BERT Cross-Encoders, LLM Ranking Comparative study of retrieval ranking approaches with phased build spec
Starbucks RecSys Pinecone, OpenAI Embeddings Recommendation engine — 85.1% NDCG

Tech Stack

Languages
ML / AI
Data & Databases
Data Engineering
Cloud & DevOps
Frameworks & APIs
Visualization

Certifications

GitHub Analytics



I build things that retrieve, reason, and rank. If that overlaps with what you're working on, reach out.

Pinned Loading

  1. Flade Flade Public

    Python

  2. Codebase-Cartographer Codebase-Cartographer Public

    Python

  3. hamilton hamilton Public

    Forked from apache/hamilton

    Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

    Jupyter Notebook

  4. kg-recommender kg-recommender Public

    Python

  5. graphrag-comparison graphrag-comparison Public

    Python

  6. sliceval sliceval Public

    Slice-based model evaluation

    Python 1