✉️ gulati9635@gmail.com 🌐https://topmate.io/gulati9635/ I’m an AI and Data Engineer specialising in building intelligent, production-ready AI systems using LLMs, RAG pipelines, and agentic frameworks. My expertise spans across LangChain, LangGraph, Vector Databases (FAISS, Chroma), FastAPI, and GCP Vertex AI, enabling me to deliver scalable, efficient, and high-impact AI applications. I help startups and enterprises integrate GenAI into their workflow, whether that’s: • Designing custom Retrieval-Augmented Generation (RAG) pipelines • Developing AI agents with LangGraph, Crew AI, and Agentic AI • Deploying LLM applications on cloud platforms like Google Cloud (GCP) & Vertex AI • Integrating Gemini and other frontier models for real-world use cases • Creating API-driven AI solutions with FastAPI for seamless integration • Hands-on experience with LLM app development & deployment • Deep understanding of AI architecture & scalability • Proven ability to translate business needs into AI solutions • Clear communication, fast delivery, and long-term collaboration mindset • Data Engineering, with specialization in Azure Data ecosystem and Python development. Excited about crafting data-driven solutions. • ~5 years of Azure cloud Data engineering experience. • Designed and implemented scalable data pipelines using Machine Learning models, Azure Data Factory and Databricks to process large datasets, Azure SQL server, ADLS, Azure blob Storage and spark with Scala and python, reducing ETL runtime by 30%. • Certified Microsoft Azure Data Engineering Associate (Cleared DP-201, DP-200, Az-900). • Experience in Hadoop (Cloudera) to Azure migration projects. • Experience in Big Data technologies like Hadoop, Hive, Impala, spark (with Scala and python), Sqoop. • Implemented Unity Catalog on Azure Databricks to unify data governance across workspaces using Azure Data Lake Storage Gen2 as the cloud storage layer. • Configured a secure Unity Catalog Metastore with Azure Managed Identity and RBAC integration for fine-grained access to datasets. • Having an additional knowledge of Unix, Shell Scripting, Python scripting, GIT, JIRA and orchestration tool- Autosys. • Was an active member and team focal for quarterly innovation championships in Amdocs.