AI/ML Systems Engineer specializing in end-to-end production systems. I build scalable AI pipelines, real-time microservices, and full-stack applications.
role: "AI Systems Engineer × Full-Stack Developer"
location: "Gujarat, India"
education: "MCA (Artificial Intelligence) @ Parul University"
focus: "LLMs, Computer Vision, Real-time Systems, Full-Stack Development"
certifications:
- "Oracle Cloud Infrastructure Gen AI Professional (2025-2027)"
- "NVIDIA Deep Learning Institute - Transformer NLP"
- "Microsoft Azure AI Document Intelligence"
building:
- "AI-powered fraud detection systems"
- "Real-time voice communication agents"
- "Automated hiring pipelines"
- "Full-stack collaboration platforms"🚀 Tech Focus: React, FastAPI, Node.js, TensorFlow, LangChain, Docker
🧠 AI/ML: LLMs, NLP, Computer Vision, RAG pipelines
🎯 Approach: End-to-end ownership from architecture to deployment
|
|
|
|
|
|
|
|
|
Real-time fraud detection system with ML-powered monitoring and Razorpay API integration.
Tech Stack: Python · FastAPI · Scikit-learn · XGBoost · Docker · WebSockets
Features:
- Real-time transaction monitoring with ML models
- WebSocket-based alert system
- RESTful API for payment monitoring
- Docker containerization for deployment
Voice-enabled AI chatbot with speech recognition and GPT-4 integration.
Tech Stack: Python · LangChain · OpenAI GPT-4 · LiveKit · FastAPI
Features:
- Real-time voice interaction
- Speech-to-text conversion
- Context-aware AI responses
- WebSocket audio streaming
Automated recruitment pipeline with OCR and NLP for resume parsing and matching.
Tech Stack: Python · Tesseract OCR · NLP · FastAPI · Docker
Features:
- PDF/image resume parsing with OCR
- Semantic matching with NLP
- Automated candidate scoring
- CI/CD pipeline with GitHub Actions
Full-stack RBAC system with task management and real-time collaboration.
Tech Stack: React.js · Vite · TailwindCSS · WebSocket
Features:
- Role-based access control (RBAC)
- Drag-and-drop task management
- Real-time synchronization
- Performance analytics dashboard
Valid: Oct 2025 – Oct 2027
exploring:
- Multi-agent AI systems and autonomous orchestration
- Real-time AI applications with low-latency inference
- RAG (Retrieval-Augmented Generation) pipelines
- Production-grade ML system deployment
learning:
- Advanced LLM engineering and prompt optimization
- Microservices architecture at scale
- Cloud-native AI/ML infrastructure
- System design for distributed applications
open_to:
- AI/ML engineering roles
- Full-stack development positions
- Technical collaborations on AI projects
- Open source contributionsInterested in collaboration or discussing AI/ML projects?
