Results-driven Data Engineer with 2.6 years of experience in designing and implementing data pipelines. Skilled in Python, AWS, SQL, and BigQuery for efficient ETL processes. Optimizes data architecture to enhance performance and scalability, driving actionable insights through advanced analytics.
Overview
3
3
years of professional experience
Work History
Data Engineer – AI & RAG Systems
Nexgile Technologies
Hyderabad
09.2025 - Current
Designed production-grade RAG systems, managing vector databases (FAISS, Pinecone, Chroma) and ensuring low-latency outputs.
Architected autonomous agent systems featuring planning, tool usage, memory, and self-correction with RAG as the core layer.
Implemented multi-agent workflows with dynamic tool calling for effective execution of complex tasks.
Integrated LLMs (Gemini, GPT, open-source) into production with custom model wrappers and optimized prompt strategies.
Established evaluation metrics and monitoring guardrails for RAG and agents to ensure reliability and governance.
Constructed scalable data ingestion and ETL/ELT pipelines for structured and unstructured data, converting raw enterprise data into high-quality knowledge for AI systems.
Deployed production-ready AI services via REST/Flask/FastAPI, ensuring secure integration with enterprise platforms.
Data Engineer/Data Science Python Developer
Nexgile Technologies
Hyderabad
11.2024 - 06.2025
Designed and implemented automated data extraction processes using OpenAI GPT API.
Developed targeted prompts to enhance company-related information retrieval.
Applied natural language processing techniques to improve accuracy of extracted data.
Employed Python scripting to automate workflows, significantly reducing manual effort.
Communicated technical details clearly to non-technical stakeholders for alignment on strategies.
Implemented serverless architecture with AWS Lambda and API Gateway for efficient data processing.
Created Lambda functions to tag companies based on predefined criteria for database integration.
Configured API Gateway to manage incoming requests, ensuring a secure interface.
Data Engineer
Nexgile Technologies
Hyderabad
12.2022 - 04.2024
Spearheaded migration from Google Cloud Bigquery to AWS S3 using AWS Glue, achieving annual cost savings and 14% performance increase.
Designed scalable data pipeline architecture for new product, supporting growth from zero to 125,000 daily active users.
Maintained data pipeline uptime at 99.8% while ingesting streaming and transactional data from eight primary sources using Athena, S3, and Python.
Automated ETL processes across billions of rows, reducing manual workload by 29% monthly.
Collaborated with clients to identify business requirements and deliver actionable reports.
Supported implementation and monitoring of controls and programs to ensure precision and efficacy.
Ingested data from various sources using SQL, Hubspot API, and RESTful APIs in Python for BI tool integration.
Communicated effectively with project managers and analysts to enhance data pipelines, driving efficiency KPIs up by 26%.
The main aim of the project is to increase the sales of the articles that are posted on the website, and analyze the data and give insights to the investors to increase the sales of articles
To consolidate the data in AWS, we have moved all the data to AWS from GCP by creating pipelines using Python and worked on partitions of tables to reduce the cost of querying in AWS as well as GCP
AI-driven automated company intelligence extraction platform
Built an AI-driven data extraction and enrichment system using OpenAI GPT APIs and Python to convert unstructured company data into structured, business-ready intelligence
Designed prompt-engineered NLP pipelines and automated workflows, significantly reducing manual research while improving extraction accuracy
Deployed a scalable serverless architecture using AWS Lambda and API Gateway for secure, cost-efficient processing, and seamless database integration
Multi-agent workflow system for automated decision and task execution
Architected a multi-agent orchestration system that decomposes complex tasks into specialized agents with planning, reflection, self-correction, and fault-tolerant execution
Implemented dynamic tool calling (APIs, databases, external services) with RAG-based memory to enable grounded, context-aware agent reasoning
Built end-to-end observability for agent decisions, tool usage, and execution paths, optimizing workflows for latency, reliability, and governance