Pankaj Gupta

About Pankaj Gupta

With over 18 years of experience in designing, developing, testing, and supporting Legacy and Cloud Data Engineering Platforms, I specialize in leveraging Python, PySpark, AWS, Snowflake, Shell Script, RDBMS & NoSQL, and cutting-edge LLM technologies.Key Expertise- LLM Application Development: Proficient in designing AI-driven applications using OpenAI\'s LLMs, including the creation of LLM objects, agents, chains, and RAG components with the LangChain framework- Data Engineering & Architecture: Extensive experience in solution architecture, developing critical data projects for leading finance companies, and building robust data pipelines, databases, and DWHs.Cloud & Data Management: Skilled in AWS services like Lambda, API Gateway, RDS, Aurora, and more, with hands-on experience in managing data ingestion, transformation, and storage using Snowflake and AWS technologies- Performance Optimization: Expertise in performance tuning, query optimization, and implementing Snowflake services such as Snowpipe, CDC, and time travel- Collaboration & Leadership: A proactive problem solver with a strong attention to detail, I thrive in collaborative environments and excel at mentoring teams.I am passionate about delivering high-quality solutions and driving innovation in data engineering and AI.

Experience

1. Developer

   Wellington Management

   Dec 2012 — Present · Boston, MA, US

   AI & Cloud Projects (Current & Past)Current Work: Azure OpenAI & Agentic Automation (JNI Project)1. Developing LLM-based enterprise applications using Azure OpenAI GPT models, LangChain, and LangGraph for agentic workflows.2. Implementing RAG pipelines with Azure Cognitive Search embeddings to deliver secure, context- aware enterprise chatbots.3. Building an AI-powered JNI automation system capable of- Reading incoming emails from a mailbox - Understanding intent & context - Generating intelligent, personalized responses - Automating end-to-end communication workflows4. Creating LLM chatbots for business operations using Azure AI services and Python-based orchestration. LLM Engineering & RAG Development1. Skilled in LLM objects, agents, chains, vector search, and retrieval-augmented generation using LangChain.2. Designing scalable AI agents and multi-step reasoning pipelines with LangGraph. Data Engineering & Cloud Architecture (AWS)1. Built high-performance data platforms for financial enterprise environments.2. Designed and implemented Enterprise Data Lake (EDL) and master data solutions on AWS.3. Developed real-time data pipelines with- AWS Lambda - Step Functions - S3 - API Gateway - Athena - Aurora / RDS - Redshift4. Automated onboarding of new datasets across Ingest → Conform → Organize → Publish stages. Performance & Data Optimization1. Experience with Snowflake including Snowpipe, CDC, Time Travel, and performance tuning.2. Built event-driven architectures for trading & risk analytics use cases.3. Developed Python Lambda functions and SQL logic to support analytics, reporting & microservices. Tech StackAzure OpenAI | LangChain | LangGraph | RAG | Cognitive Search | AWS | Lambda | S3 | Step Functions | Aurora | Athena | Redshift | Snowflake | Python | APIs | Microservices | Financial Data Systems

Education

• Motilal Nehru National Institute Of Technology

  B. Tech, Computer science & Engineering

Skills

• Web Services
• Servlets
• Java
• Junit
• Xml
• Java Enterprise Edition
• Sdlc
• Integration
• Oracle
• Linux
• Hibernate
• Core Java
• Soa
• Agile Methodologies
• Eclipse
• Software Development
• Agile
• Unix
• Sysbase
• Struts
• Mysql
• J2ee
• Spring
• Jsp