AI Product Engineer with hands-on experience building LLM-powered applications, production RAG systems, and agentic AI workflows.
Currently working as an AI Engineer Intern at Rubixe AI Solution Company, where personally contributed to data preprocessing, exploratory data analysis, feature engineering, model implementation, perf[...]
Specialization:
- Building AI products with LLMs (LangChain, LangGraph, Google Gemini)
- Designing & implementing RAG systems for real-world use cases
- Creating agentic AI workflows and autonomous agents
- Mobile app development with React Native & modern backends
Career Goal: AI Product Engineer | Applied AI Engineer | Gen AI Engineer | ML Engineer
- Built Production AI Systems: Designed and deployed RAG pipelines for intelligent document processing
- Mobile AI Integration: Developed AI-powered Nutri Ninja app with real-time inference and local caching
- End-to-End AI Products: Shipped full-stack AI applications from design to production
- LLM Engineering: Expertise in prompt optimization, retrieval augmentation, and agentic workflows
An intelligent nutrition assistant that scans packaged food barcodes and provides instant health insights with AI-powered diet advice.
Features:
- Real-time barcode recognition with ML inference
- AI-powered diet chatbot (LLM integration)
- Health scoring algorithm with ingredient analysis
- Local data storage for privacy
- Cross-platform support (React Native + Expo)
Tech Stack: React Native | TypeScript | FastAPI | Python | AI/ML models | Firebase
Impact: Processed nutrition data for 20+ food items with personalized recommendations
Repository: Nutri-Ninja-5.0
Production-ready conversational AI system leveraging LangChain for orchestration and Google Gemini for intelligent responses.
Features:
- Multi-turn conversation with context management
- LLM-powered responses with real-time streaming
- Memory management for context retention
- Environment-based secure configuration
- Error handling & retry logic
- Extensible architecture for production systems
Tech Stack: Python | LangChain | Google Gemini API | Python-dotenv
Use Case: Foundation for customer support systems, internal Q&A platforms, educational assistants
Repository: Agent-Chat-Bot
Computer vision system for real-time facial emotion detection with music-based mood responses and analytics dashboards.
Features:
- Live emotion classification (Happy, Sad, Angry, Neutral, etc.)
- Adaptive music player based on detected emotions
- Web & PyQt dashboards for emotion analytics
- CSV/SQLite logging for emotion tracking
- Educational & demo use cases
Tech Stack: Python | DeepFace | OpenCV | PyQt | Flask | SQLite
Applications: Behavioral analysis, educational tools, interactive installations
Repository: Emotion-Detection
Computer vision model for detecting and classifying furniture items in images using state-of-the-art YOLO architecture.
Tech Stack: YOLOv8 | Python | OpenCV | Jupyter
Repository: YOLOv8_Furniture_Object_Detection
An intelligent agentic system designed to maintain contextual memory and retrieve relevant information dynamically using Qdrant vector search for smarter, more personalized AI interactions.
Features:
- Long-term conversational memory using vector embeddings
- Semantic retrieval with Qdrant for contextual recall
- Agent workflow for task-aware responses
- Efficient document and conversation memory indexing
- Scalable architecture for AI assistant applications
Tech Stack: Python | LangChain | Qdrant | FastAPI | Vector Search | LLM APIs
Use Case: Smart assistants, enterprise knowledge bots, and memory-driven conversational AI systems
Repository: Agent_with_Qdrant_Memory
An AI-powered travel assistant built to help users explore travel options, plan itineraries, and answer destination-related queries with conversational intelligence.
Features:
- Travel itinerary guidance and recommendations
- AI-driven conversations for destination planning
- Context-aware responses for user travel preferences
- Smart agent workflows for task assistance
- Scalable conversational interface for travel support
Tech Stack: Python | LangChain | LLM APIs | FastAPI | Vector Memory | Agent Workflows
Use Case: Travel planning assistants, trip guidance systems, and AI-powered customer support experiences
Repository: Yatra_Agent
| Project | Topics | Repository |
|---|---|---|
| Python Fundamentals & Games | Core Python, OOP, Game Development | Python-Code-Fundamentals-and-Games |
| Data Science Stack | NumPy, Pandas, Matplotlib fundamentals | Pandas_Practice | Numpy_Practice |
| Machine Learning | ML algorithms, model training, evaluation | Machine-Learning-Project |
| Computer Vision | MobileNet Transfer Learning for mobile deployment | Computer-Vision-MobileNet_Transfer-Learning |
| DSA Practice | Data Structures & Algorithms problem solving | DSA_Practice_Problem |
- Advanced RAG architectures (Multi-agent retrieval, Hybrid search strategies)
- LLM fine-tuning and advanced prompt engineering
- Production-grade AI systems with FastAPI + Docker
- Scaling AI applications with cloud platforms (GCP, AWS)
- Multi-agent AI systems and orchestration patterns
I am actively interested in discussing AI engineering, LLM applications, and innovative product development opportunities.
Open to: Full-time Applied AI Engineer / Junior AI Engineer | Gen AI Engineer | Python Backend Engineer (AI focused) | ML Engineer | AI Product Engineer roles
Contact:
- Email: dewanganjitendra725@gmail.com
- LinkedIn: linkedin.com/in/jitendradewangan/
- GitHub: github.com/JitendraDew009
Learn → Build → Ship → Iterate → Repeat
Core Principles:
- Writing clean, maintainable, and well-documented code
- Building features with measurable real-world impact
- Continuous learning and technical exploration
- Shipping production-ready solutions
If my projects have been helpful, please consider starring them.
Last updated: November 2026