class MohitChandraFulara: def __init__(self): self.name = "Mohit Chandra Fulara" self.role = "AI & ML Developer | MCA Student" self.university = "K.R. Mangalam University, Gurgaon (2027)" self.location = "Uttarakhand, India" self.focus = ["Agentic AI", "RAG Pipelines", "LLMs", "Multi-Agent Systems"] self.languages = ["Python"] self.currently = "Building Multi-Agent AI SOC Platform " def say_hi(self): print("Thanks for dropping by! Let's build something intelligent ")Stack: Python · LangChain · LangGraph · FAISS · FastAPI · Docker · Kafka · Ollama · Llama3 · MITRE ATT&CK
- Upgraded AI-Based Security Log Analyzer into a full Multi-Agent SOC Platform using LangGraph
- Designed agent pipeline:
Kafka Stream → Correlation Agent → Intelligence Agent (RAG) → Risk Agent → Response Agent - Built threat intelligence using RAG with FAISS & MITRE ATT&CK framework
- Automated risk scoring & incident response decision-making
- Integrated Ollama + Llama3 for local LLM-powered threat analysis
Stack: Python · EfficientNet · HuggingFace Transformers · Scikit-learn · Matplotlib
- Built a multimodal AI system to detect whether text and images are AI-generated or human-written
- Text detection using
Hello-SimpleAI/chatgpt-detector-robertawith confidence scoring - Image detection using EfficientNet architecture to identify AI-generated visual inconsistencies
- Full preprocessing, tokenization & feature extraction pipelines
- Evaluated with accuracy, precision, recall, F1 Score & ROC AUC
Stack: Python · FAISS · Sentence Transformers · FastAPI · RAG
- Built AI-powered system to intelligently analyze and query large-scale security logs
- Implemented RAG pipeline using sentence embeddings + FAISS-based vector search
- Designed log ingestion, preprocessing, chunking & embedding workflows
- Enabled natural language querying over logs to detect anomalies & suspicious activities
- Automated manual log inspection, reducing investigation time significantly
Stack: Python · LangChain · FAISS · HuggingFace · RAG · LLM
- Analyzed multi-page legal documents to extract executive summaries, key risks & contractual obligations
- Implemented RAG using vector embeddings and similarity search for context-aware clause understanding
- Designed full pipeline: document ingestion → chunking → embedding → querying
- Automated manual summarization & risk identification for faster document review
- 🏅 Python Fundamentals for Beginners — Simplilearn
- 🏅 Machine Learning using Python — Simplilearn
Connect with Me
⭐ Star some repos if you find them useful!