Agentic GenAI & RAG Engineer

Raghvendra Singh

**********************@*****.*** +91-812******* Linkedin Github

EDUCATION

Galgotias University

B.Tech in Computer Science

Credit-Linked Program in AI & ML (15 academic credits) — Daksh Gurukul, IIT Guwahati (Ongoing) PROFILE SUMMARY

AI/ML Engineer focused on building production-oriented GenAI and Agentic AI systems. Experienced in developing multi-agent architectures, RAG pipelines, MCP-based tool integrations, and LLM-powered applications using Python and FastAPI. Hands-on experience with Docker, AWS, vector databases, semantic retrieval, and deploying scalable AI systems. EXPERIENCE

Your Pharma Healthcare Data Analyst Intern Jan 2026- Jun 2026

● Analyzed and cleaned pharmaceutical sales and operational data using Excel/SQL to identify trends, discrepancies, and key performance indicators.

● Created reports and dashboards to visualize business metrics and deliver actionable insights for data-driven decision- making.

FZD Digital Cable Network Part-time Dec 2024 – Jan 2026

● Analyzed and maintained operational data for the cable TV network, preparing reports and identifying data discrepancies to support day-to-day operations.

● Assisted with server maintenance and troubleshooting, helping ensure system reliability and smooth network operations.

PROJECTS

Nexus AI :

Tools: Python, FastAPI, Multi-Agent Systems, MCP, Groq, Docker, AWS ECS, Amazon ECR, AWS IAM, AWS Secrets Manager, Git, GitHub.

● Engineered a multi-agent AI operations platform using Python and FastAPI, with specialized agents coordinated through an orchestration and planning layer.

● Integrated Model Context Protocol (MCP) to enable agents to interact with external capabilities through Web, Filesystem, and GitHub MCP servers.

● Built shared services for LLM inference, memory, prompt management, configuration, and observability, using Groq for production LLM execution.

● Containerized and deployed Nexus AI on AWS ECS using Docker and Amazon ECR, securing API credentials with AWS Secrets Manager and IAM.

Deal Analyzer Enterprise AI contract Intelligence Platform: Tools: Python, Streamlit, FastAPI, Google Gemini, Qdrant, Sentence Transformers, RAG, Multi-Agent AI, MCP, Docker

● Built an enterprise-grade AI Contract Intelligence Platform using RAG, Multi-Agent AI, and an MCP-inspired tool architecture to analyze legal, financial, and compliance risks from PDF contracts.

● Designed a semantic retrieval pipeline using Sentence Transformers, Qdrant Vector Database, and Google Gemini, enabling agents to retrieve context and invoke external tools through the MCP layer.

● Developed modular AI agents with orchestration logic, integrating an MCP client/server architecture for tool execution alongside retrieval and LLM-based reasoning.

Customer Churn Prediction:

Tools: Python, Pandas, NumPy, Scikit-learn, XGBoost, Streamlit, Matplotlib, Joblib

● Developed a customer churn prediction model using Logistic Regression, Random Forest, and XGBoost, selecting the best model based on recall-focused evaluation.

● Improved model performance using hyperparameter tuning (GridSearchCV) and threshold optimization to maximize churn detection.

● Deployed the model using Streamlit and provided business insights through feature importance and ROC-AUC analysis.

SKILLS

Programming & ML: Python, SQL, Scikit- learn, Machine Learning, NLP, PyTorch, Transformers, BERT GenAI & Agentic AI: RAG, LLM Applications, Multi-Agent Systems, MCP, Prompt Engineering, Semantic Search, Vector Search, Sentence Transformers, FAISS, Qdrant. Data & Tools: FastAPI, Streamlit, REST APIs, Docker, AWS ECS, Amazon ECR, AWS IAM, Secrets Manager.

Contact this candidate