Available for Generative AI roles

Generative AI Engineer building LLM and RAG systems.

Five years across full-stack, DevOps, and MLOps. I build LLM chatbots, retrieval pipelines, and document-processing tools — from prompt engineering and vector search through FastAPI services and cloud deployment.

Vishal Yadav Chatharasi
About

Turning language models into products people use

I'm a Generative AI Engineer with around five years spanning full-stack development, DevOps, and MLOps. I build LLM-powered applications and RAG systems with the OpenAI and Claude APIs, LangChain, and vector databases.

The part I care about is what happens after the prototype — containerizing services, shipping them to AWS and GCP behind CI/CD, and keeping them observable once real traffic arrives.

Location
New Jersey, US
Focus
LLM apps, RAG, AI agents
Education
M.S. Computer Software Engineering
Status
Open to new roles
Stack

Tools I work with

Core stack

Python
FastAPI
AIOpenAI
Claude
LangChain
Hugging Face
PcPinecone
Pandas
NumPy
Docker
awsAWS
Google Cloud
PostgreSQL
Git
React
TypeScript

Detailed breakdown

Generative AI & LLMs

GPT-4GPT-3.5ClaudeOpenAI & Claude APIs RAGPrompt EngineeringLangChainHugging Face PineconeChromaFAISSEmbeddings Semantic SearchAI AgentsChatbots & Q&A

Languages & Web

PythonTypeScriptJavaScript (ES6+)SQL HTML5/CSS3ReactNode.jsFastAPI StreamlitREST APIs

Cloud, DevOps & MLOps

AWS (Lambda, S3, EC2, ECS)Google Cloud (Vertex AI)Docker KubernetesCI/CD (Jenkins, GitHub Actions)Terraform AnsibleMLflowAirflowPrometheusGrafana

Databases & Tools

PostgreSQLMySQLSupabaseGit & GitHub JupyterPostmanVS CodeAgile/Scrum
Work

Selected projects

A selection of AI, Web3, and developer-tooling projects — all open source on GitHub.

Experience

Where I have worked

Software Developer

May 2025 – Present

Fusion IT Tek Inc · North Carolina

  • Build full-stack applications with React, TypeScript, and Python (FastAPI) across front end, back end, and REST APIs.
  • Ship Generative AI features — RAG pipelines with GPT-4 / Claude, Pinecone, and LangChain for context-aware responses.
  • Design AI agent workflows and deploy LLM-powered services to AWS / GCP with Docker and CI/CD.

MLOps Engineer

2022 – 2023

Stackblocks Labs · Hyderabad, IN

  • Built and automated ML pipelines for training, versioning, and deployment with MLflow, Docker, and Kubernetes.
  • Orchestrated workflows with Apache Airflow and DVC, and monitored models for drift with Prometheus and Grafana.
  • Operationalized early LLM workloads — serving and evaluating GPT-3.5 and open-source models for internal prototypes.

DevOps Engineer

2020 – 2022

Honnex Software Solutions · Hyderabad, IN

  • Designed and maintained CI/CD pipelines with Jenkins and GitHub Actions to automate build, test, and deployment.
  • Containerized apps with Docker on Kubernetes and provisioned AWS (EC2, S3, ECS) with Terraform and Ansible.
  • Set up monitoring and alerting with Prometheus, Grafana, and the ELK stack to reduce downtime.

Web Developer (Intern)

2019 – 2020

Honnex Software Solutions · Hyderabad, IN

  • Built responsive, cross-browser interfaces with HTML5, CSS3, JavaScript (ES6), Bootstrap, and jQuery.
  • Developed React components consuming REST APIs, and supported Node.js/Express and MySQL back-end features.
Education

Education & certifications

M.S., Computer Software Engineering

Aug 2023 – May 2025

Cleveland State University · Cleveland, OH

GPA
3.7 / 4.0
Coursework
Software Engineering, Operating Systems, Computer Networks II, Database Systems

B.Tech, Computer Science

Aug 2018 – Jul 2022

Sreyas Institute of Engineering and Technology · Hyderabad, TS, India

GPA
3.7 / 4.0
Coursework
Software Engineering, Operating Systems, Computer Networks II, Database Systems
Contact

Let’s work together

Open to Generative AI and LLM engineering roles. Email is the fastest way to reach me.