Anurag Sathe

AI/ML Developer with hands-on experience building production-grade agentic AI systems, LLM applications, and RAG pipelines using LangChain, LangGraph, and Microsoft AutoGen. Skilled in designing multi-agent architectures, integrating LLMs (GPT-4o, Claude, Llama) with real-time external APIs, and deploying scalable FastAPI microservices on AWS and Azure. Strong foundation in Python, data engineering, and MLOps, with proven ability to translate research-grade AI concepts into reliable, testable, enterprise-ready systems.

Associate Data Engineer - CloudNexus - Bhopal, India

(2026-02 - 2026-08)

• Architected and deployed production-grade ETL/ELT pipelines processing 500GB+ daily enterprise datasets using AWS Glue, Apache Spark, and Databricks, reducing analytical query execution time by 35 and enabling real-time business intelligence
• Designed cloud-native ingestion workflows integrating AWS S3, Lambda, EventBridge, and Step Functions with Apache Kafka for high-throughput, low-latency data ingestion supporting both batch and real-time processing modes
• Built automated data quality validation framework achieving 99+ data consistency across production pipelines using Python validators and Databricks Delta Lake, preventing downstream analytics failures and data-driven decision errors
• Orchestrated enterprise data consolidation from Salesforce, MySQL, SQL Server, PostgreSQL, and Azure SQL using API-driven patterns and change data capture, enabling unified analytics across disparate systems
• Implemented feature engineering pipelines for ML/GenAI applications with Apache Airflow and AWS Step Functions, reducing model training time by 28 through intelligent data preparation and feature selection
• Developed containerized FastAPI microservices with Docker and GitHub CI/CD, enabling rapid iteration and zero-downtime deployments in production environments

Bachelor of Technology - Computer Science and Engineering - Technocrats Institute of Technology & Science Bhopal (2022 - 2026)