Kartikey Sharma
0%
Available for Freelance

Building
Autonomous

AI
Systems
That

Actually
Ship

AI Agent Developer specializing in LangGraph orchestration, FastAPI backends, and production-grade full-stack AI. MNIT Jaipur B.Tech 2025.

0
Projects Shipped
0
Companies
MNIT Jaipur
Tier-1 College
Kartikey Sharma
Kartikey Sharma
AI Agent Developer · ML Engineer
Jaipur, Rajasthan, India
Open to freelance projects
Automations · Agentic AI · Production Grade · MNIT Jaipur · Automations · Agentic AI · Production Grade · MNIT Jaipur ·
LangGraph
LangChain
FastAPI
Groq API
GPT-4o
React + Vite
ChromaDB
Docker
Python
Prompt Engineering
SSE Streaming
Multi-Agent Systems
RAG Pipeline
Sentence Transformers
LangGraph
LangChain
FastAPI
Groq API
GPT-4o
React + Vite
ChromaDB
Docker
Python
Prompt Engineering
SSE Streaming
Multi-Agent Systems
Work History

Where I've
Built & Contributed

Jyesta
Professional AI Engineer — EdTech
Jyesta Corporate Entity Pvt. Ltd.
Architecting intelligent AI tutoring agents for EdTech platforms — enabling personalized, adaptive learning at scale.
Building LangGraph-powered multi-agent pipelines that automate curriculum delivery, doubt resolution, and student progress tracking.
Integrating LLM APIs (GPT-4o, Groq LLaMA) for real-time educational content generation with structured JSON output enforcement.
Designing RAG-based knowledge systems allowing students to query course material naturally with semantic context-aware responses.
JURRYITECH
Agentic AI Engineer — Patent Drafting
JURRYItech
Building agentic AI systems for automated patent drafting — extracting technical claims and generating structured patent language compliant with IP filing standards.
Designing multi-step LangGraph agents that parse invention disclosures, identify novelty, and produce legally structured patent draft documents.
Integrating legal knowledge bases via RAG pipelines to ground patent outputs in prior-art context and domain-specific terminology.
Collaborating with IP professionals to refine agent prompting strategies for accuracy in high-stakes legal document generation.
Celebso
AI Engineer — Platform Development Running
Celebso · India's Premium Creator & Innovator Platform
Building AI-powered features for Celebso — India's premium platform for creators, founders, entrepreneurs, and professionals to build visibility and grow their influence.
Developing intelligent profile recommendation and discovery engines using semantic search and vector embeddings to connect talent with investors and industry leaders.
Engineering AI agents to automate startup pitch analysis, talent evaluation, and event participation workflows across Celebso's creator ecosystem.
Integrating LLM capabilities to personalize the platform experience — helping users build powerful professional brands and get discovered faster. (celebso.com)
Ooglesoft
Machine Learning Engineer
Acsivi Group of Companies (Ooglesoft)
Designed and deployed ML-driven backend services using FastAPI and Flask for classification and recommendation use cases.
Integrated LLM APIs to automate content generation and enforce consistent structured JSON outputs in production.
Implemented response validation layers and guardrails — significantly improving reliability of AI-generated responses.
Collaborated with senior engineers to optimize AI workflows for live product features serving real users.
Aurion Pro
Data Analyst Intern — AI-Augmented Analytics
Aurion Pro · JANAADHAR Government Project
Data validation and workflow analysis for a large-scale citizen database system, leveraging AI-assisted anomaly detection tools.
Applied machine learning techniques to automate data quality checks and flag inconsistencies in high-volume government datasets.
Built AI-augmented reporting pipelines and test-case validation workflows, improving processing accuracy across the JANAADHAR initiative.
0
Projects Shipped
0
Companies & Projects
0
Avg Quality Score
0
% Production Ready
Selected Work

12 Production-Grade
AI Systems

Multi-Agent Customer Support
Multi-Agent System
Flagship
Multi-Agent Customer Support System

Enterprise-grade AI platform that autonomously routes, triages, and resolves customer support tickets. Built with LangGraph state machines coordinating specialized triage, knowledge retrieval, and resolution agents with full conversation memory and context awareness.

LangGraphGroq APIChromaDBFastAPIReactDocker
Automation Studio
Automation Platform
Open Source
Automation Studio

AI-powered workflow automation platform that runs 100% locally using open-source models. Features autonomous agents for research, analysis, content creation, visual workflow builder, vector memory, and event-driven automation—all without API costs or data privacy concerns.

OllamaFastAPIChromaDBPythonLocal AI
I Am Personal AI
Personal AI
I Am Personal AI

Full-stack personal AI assistant with real-time chat via WebSocket, intelligent reminders, alarms with push notifications, and a beautiful Progressive Web App interface. Features Firebase Cloud Messaging, activity dashboard, and quick actions for daily productivity.

FastAPIWebSocketPWAFirebasePython
FinanceIQ
Finance AI
FinanceIQ

Intelligent financial analysis platform that transforms raw financial data into actionable insights. Features automated spending pattern analysis, anomaly detection, budget recommendations, and beautiful visual dashboards for comprehensive financial intelligence.

LangGraphGroqPandasData AnalysisFastAPI
TravelBuddy
Travel AI
Deployed
TravelBuddy

Multilingual AI travel companion with GPS-powered location discovery, personalized itinerary recommendations, and persistent conversation memory. Features Groq + Gemini fallback for reliable responses, Google Places integration, and seamless travel planning experience.

FlaskGoogle PlacesGroqGeminiDocker
App Builder
Multi-Agent · Coding
App Builder

Revolutionary natural language to production-ready code system. Multi-agent architecture with Planner, Architect, and Coder agents working together to simulate real software development workflows—from concept to deployment-ready applications.

LangGraphGroqPythonMulti-Agent
Dr. Research
Research AI
Dr. Research

Advanced AI research assistant that autonomously conducts comprehensive research, analyzes multiple sources, synthesizes findings, and generates detailed research reports. Features intelligent source validation, citation management, and structured output formatting.

LangGraphReActResearchAI Agent
NeuralBase
Neural Network
NeuralBase

Comprehensive neural network framework and experimentation platform. Build, train, and deploy deep learning models with advanced architectures, hyperparameter optimization, and production-ready model serving capabilities.

PyTorchTensorFlowNeural NetworksML
DriveMeDATA
Data Platform
DriveMeDATA

Intelligent data management and analytics platform that drives actionable insights from complex datasets. Features automated data pipelines, real-time processing, advanced analytics, and visualization tools for data-driven decision making.

Data EngineeringAnalyticsPythonETL
ReviewMeSir
Review System
ReviewMeSir

AI-powered review management and analysis system that intelligently processes, categorizes, and extracts insights from customer reviews. Features sentiment analysis, trend identification, and automated response generation for enhanced customer engagement.

NLPSentiment AnalysisFastAPIAI
Stock Price Prediction
Machine Learning
Stock Price Prediction

Advanced machine learning system for stock market price forecasting using historical data analysis. Features comprehensive feature engineering, multiple regression models, performance evaluation metrics, and interactive visualization dashboards for financial insights.

PythonPandasScikit-learnTime Series
Crop Yield Prediction
Machine Learning
Crop Yield Prediction

Agricultural intelligence platform predicting crop yields using machine learning regression models. Features comprehensive exploratory data analysis, advanced feature engineering, climate and soil factor integration, and impact visualization for sustainable farming decisions.

PythonPandasNumPyScikit-learnAgriculture
What I Build

AI Solutions for
Real Business

AI Agent Development

Custom autonomous agents using LangGraph — ReAct, self-reflection, task decomposition. From single tools to complex multi-agent orchestration with memory.

Workflow Automation

Replace manual processes with intelligent AI pipelines. Customer support, document processing, research workflows — running reliably without human intervention.

RAG & Knowledge Systems

Intelligent Q&A over your documents using vector embeddings and ChromaDB. Understands context, not just keywords.

Full-Stack AI Apps

React frontend + FastAPI backend + Docker. Real-time streaming, beautiful UIs, production-ready. Full product, not just an API wrapper.

Prompt Engineering

Structured architectures, JSON enforcement, hallucination reduction, guardrails. Making LLMs reliable and consistent in production.

ML & Data Analysis

Supervised/unsupervised models, feature engineering, intelligent dashboards. Raw data into actionable business intelligence.

Technical Expertise

Full Tech
Stack

AI / LLM
LangGraph
LangChain
Groq (LLaMA 3.3 70B)
OpenAI GPT-4o
Gemini API
Sentence Transformers
Prompt Engineering
Backend
Python
FastAPI
Flask
ChromaDB
SQLite / Redis
Docker
SSE Streaming
Frontend & ML
React + Vite
Tailwind CSS
Recharts
Scikit-learn
PyTorch / TensorFlow
Pandas / NumPy
Hugging Face
AI Patterns
ReAct Agents
Self-Reflection
Task Decomposition
Multi-Agent Graphs
RAG Pipeline
JSON Enforcement
Guardrails & Validation
How I Work

Idea to
Deployed Product

01
Understand the Problem

Deep dive into your workflow. What's manual? What costs time? I map the exact process before writing a single line of code.

02
Design the Architecture

Design the LangGraph state machine — agents, tools, handoffs, data flow. The right architecture determines everything.

03
Build & Iterate

Real LLM integrations from day one. Weekly demos, constant feedback, no surprises. You see progress every step.

04
Ship Production-Ready

Docker, error handling, health checks, documentation. Not a demo — a system your team can rely on every day.

What Clients Say

Honest feedback from
real projects

"Very solid work. The multi-agent support system actually reduced our manual workload. We had a few iterations on the prompts, but Kartikey was quick to fix things."

Rohan profile photo
Rohan M.
CTO, SaaS Startup

"Good experience overall. The research agent saves us time on desk research. We still tweak it sometimes for niche topics, but the base system is strong."

Sarah profile photo
Sarah K.
Head of Research

"Understood our requirements quickly and shipped on the agreed timeline. Some edge cases came up later, but he helped us handle them without drama."

Aarav profile photo
Aarav P.
Founder, AI Agency

"The finance tool is now part of our workflow. UI is clean, and streaming responses feel nice. There were a couple of minor bugs at launch, but they were fixed fast."

Priya profile photo
Priya S.
Product Manager

"Knows his way around production AI. Not just fancy demos. The RAG system is reliable enough that our team actually uses it daily."

Marcus profile photo
Marcus L.
Senior Engineer

"Easy to communicate with and open to feedback. We did not write long reviews, but overall it was a good collaboration."

Neha profile photo
Neha T.
Operations Lead

"Very solid work. The multi-agent support system actually reduced our manual workload. We had a few iterations on the prompts, but Kartikey was quick to fix things."

Rohan profile photo
Rohan M.
CTO, SaaS Startup

"Good experience overall. The research agent saves us time on desk research. We still tweak it sometimes for niche topics, but the base system is strong."

Sarah profile photo
Sarah K.
Head of Research

"Understood our requirements quickly and shipped on the agreed timeline. Some edge cases came up later, but he helped us handle them without drama."

Aarav profile photo
Aarav P.
Founder, AI Agency

"The finance tool is now part of our workflow. UI is clean, and streaming responses feel nice. There were a couple of minor bugs at launch, but they were fixed fast."

Priya profile photo
Priya S.
Product Manager

"Knows his way around production AI. Not just fancy demos. The RAG system is reliable enough that our team actually uses it daily."

Marcus profile photo
Marcus L.
Senior Engineer

"Easy to communicate with and open to feedback. We did not write long reviews, but overall it was a good collaboration."

Neha profile photo
Neha T.
Operations Lead
FAQ

Frequently Asked
Questions

What services do you offer? +
I specialize in AI agent development using LangGraph, full-stack AI applications (React + FastAPI), RAG and knowledge systems, workflow automation, prompt engineering, and ML/data analysis. If it involves making AI reliable in production, that's my zone.
How much do you charge? +
Pricing depends on project scope. I offer hourly rates ($30–60/hr) or fixed-price project quotes. Most small-to-medium AI agent projects fall between $500–$2000. Email me and I'll send a detailed quote within 24 hours.
What does your development process look like? +
Discovery call → architecture design → iterative build with weekly demos → production delivery with Docker, docs, and deployment support. You always see progress, no surprises.
Can you work with my existing tech stack? +
Yes. I build standalone AI agents that integrate via APIs, or I work within your current stack. My FastAPI backends are modular and designed to plug into existing infrastructure easily.
Do you sign NDAs / keep projects confidential? +
Yes. I can sign an NDA, work under confidentiality clauses, and follow your security requirements. If needed, I can also work inside your GitHub org with limited access.
Do you provide post-launch support? +
Yes. I offer a handover with documentation, monitoring guidance, and a support window for bug fixes. Ongoing maintenance and feature iterations are available as a monthly retainer.
What do you need from me to get started? +
A quick brief (goals, users, success metrics), any existing docs/APIs, and sample inputs/outputs. After a short discovery call, I’ll share a clear scope, timeline, and quote.
How long does a project typically take? +
Simple AI integrations: 1–2 weeks. Single agent tools: 2–3 weeks. Multi-agent systems or full-stack apps: 3–6 weeks. I give accurate timelines upfront and I hit them.
Available for freelance — starting immediately
Got a project?
Let's build together.

Whether it's automating a workflow, building a custom AI agent, or adding intelligent features to your product — I'm ready. Response within 24 hours.

✉ Email Me LinkedIn GitHub
--:--
IST
Available Timezones
India (IST)
Asia/Kolkata
--:--
Europe (CET)
Europe/Berlin
--:--
US (EST)
America/New_York
--:--