Looking for a job

Kaustubh Tiwari

@kaustubhtiwari1

Message

I build production-oriented LLM, RAG, and multi-agent AI applications that automate data-driven workflows.

India

Message

What I'm looking for

I'm looking to build production-oriented LLM applications, multi-agent systems, RAG pipelines, and automated data-driven AI workflows from prototype through deployment.

I've built AI products including VentureOS, a multi-agent venture studio that turns startup ideas into investor-ready strategies using RAG, vector search, persistent memory, n8n, Gemini, PostgreSQL/pgvector, and Supabase.

I also built an open-source academic paper analyzer that detects plagiarism and six forms of bias. By parallelizing API execution, I reduced analysis time from approximately 100 seconds to 35 seconds and shipped it with a FastAPI backend and React/Vite frontend.

At Zyrixcraft, I developed Python-based NLP and LLM automation pipelines using the OpenAI API, Pandas, NumPy, and scikit-learn to classify unstructured business data and automate analytics workflows. Earlier at CodSoft, I developed and evaluated machine-learning models for classification and prediction tasks.

I'm focused on taking AI systems from data preparation and exploratory analysis through agent orchestration, API integration, and deployment.

Experience

Work history, roles, and key accomplishments

AI Intern

Zyrixcraft

Mar 2025 - Oct 2025 (7 months)

Developed NLP and LLM-powered automation pipelines in Python using OpenAI API, Pandas, NumPy, and scikit-learn to process and extract insights from unstructured business data. Performed data preprocessing, feature engineering, and model experimentation, building end-to-end ML workflows in Jupyter.

Python OpenAI API Pandas NumPy scikit learn NLP LLM data preprocessing Feature Engineering Jupyter

AI/ML Intern

CodSoft

Sep 2024 - Nov 2024 (2 months)

Developed machine learning models in Python for classification and prediction tasks using Pandas, NumPy, and scikit-learn. Performed data cleaning, exploratory data analysis, feature selection, and model training and evaluation using standard ML metrics.