# CV -- Tejesh Mattaparthi

**Location:** United States (Open to Relocate)
**Email:** tejesh.m@cvmailhub.com
**LinkedIn:** linkedin.com/in/tejesh-mattaparthi-26b458208

## Professional Summary

AI Engineer with 3 years of experience designing, building, and deploying enterprise AI solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, and scalable machine learning pipelines across cloud environments. Experienced in developing intelligent assistants, semantic search platforms, document intelligence systems, and production AI services using Python, LangChain, LangGraph, FastAPI, PyTorch, TensorFlow, AWS, Azure OpenAI, and Google Vertex AI.

## Experience

### JPMorgan Chase & Co. -- AI Engineer
Aug 2025 -- Present

- Designed enterprise AI applications using LLMs, LangChain, LangGraph, and RAG, improving response accuracy by 36%.
- Developed scalable AI pipelines with Python, FastAPI, AWS Bedrock, and SageMaker, processing 80M+ records monthly while reducing inference latency by 41%.
- Built multi-agent AI workflows integrating function calling, MCP, enterprise APIs, and vector databases, reducing manual operations by 38%.
- Implemented semantic search using Sentence Transformers, FAISS, Pinecone, and OpenAI embeddings, decreasing retrieval time by 63%.
- Optimized LLM performance through prompt engineering, retrieval tuning, evaluation frameworks, and response validation, reducing hallucinations by 31%.
- Deployed production AI services using Docker, Kubernetes, MLflow, GitHub Actions, and CI/CD.

### Zensar Technologies -- AI/ML Engineer
May 2021 -- Jun 2023

- Built predictive ML solutions using Python, SQL, XGBoost, Random Forest, and Logistic Regression.
- Engineered ETL pipelines using PySpark, Apache Spark, SQL, dbt, and Apache Airflow.
- Created NLP applications using LangChain, Hugging Face Transformers, BERT, and RAG.
- Automated ML experimentation using MLflow, Docker, GitHub Actions, and CI/CD.

## Projects

### Enterprise AI Copilot Platform
Python, LangChain, LangGraph, FastAPI, OpenAI, Vertex AI, FAISS, Docker

- Built an enterprise AI copilot using LangChain, LangGraph, and RAG across 100K+ internal documents.
- Supported 750K monthly inference requests with FastAPI, Docker, Vertex AI, vector search, and AI agents.
- Reduced hallucinated responses by 28% through retrieval tuning and evaluation workflows.

### Intelligent Document Processing Platform
Python, FastAPI, Hugging Face, AWS, PostgreSQL, ChromaDB

- Designed an AI-powered document processing platform for extraction, classification, and validation.
- Reduced manual processing time by 65% and improved document processing accuracy by 32%.
- Improved deployment reliability with MLflow, GitHub Actions, and Docker.

## Education

- MS in Computer Science, University of Central Missouri, USA (May 2026)

## Skills

Python, SQL, TypeScript, JavaScript, LangChain, LangGraph, LlamaIndex, RAG, AI Agents, MCP, PyTorch, TensorFlow, scikit-learn, Hugging Face, FAISS, Pinecone, ChromaDB, Weaviate, AWS Bedrock, SageMaker, Azure OpenAI, Vertex AI, FastAPI, Docker, Kubernetes, MLflow, GitHub Actions, CI/CD, PostgreSQL, MongoDB, Redis.