I am a Software Engineer with 3+ years of experience building and deploying scalable, production-grade systems across cloud, data, and AI platforms. I am proficient in Python, SQL, distributed systems, and cloud-native architectures, with hands-on experience in LLMs, RAG pipelines, real-time data processing, and end-to-end software delivery in customer-facing environments. In my recent roles, I architected end-to-end vector data pipelines, built a RAG-based GenAI framework, and created NLP-based agent workflows to automate marketing intelligence, delivering scalable insights and improving reliability. I also optimized inference and retrieval pipelines for lower latency and 24/7 production stability.

RAGAMALIKA KARUMURI

I am a Software Engineer with 3+ years of experience building and deploying scalable, production-grade systems across cloud, data, and AI platforms. I am proficient in Python, SQL, distributed systems, and cloud-native architectures, with hands-on experience in LLMs, RAG pipelines, real-time data processing, and end-to-end software delivery in customer-facing environments. In my recent roles, I architected end-to-end vector data pipelines, built a RAG-based GenAI framework, and created NLP-based agent workflows to automate marketing intelligence, delivering scalable insights and improving reliability. I also optimized inference and retrieval pipelines for lower latency and 24/7 production stability.

Available to hire

I am a Software Engineer with 3+ years of experience building and deploying scalable, production-grade systems across cloud, data, and AI platforms. I am proficient in Python, SQL, distributed systems, and cloud-native architectures, with hands-on experience in LLMs, RAG pipelines, real-time data processing, and end-to-end software delivery in customer-facing environments.

In my recent roles, I architected end-to-end vector data pipelines, built a RAG-based GenAI framework, and created NLP-based agent workflows to automate marketing intelligence, delivering scalable insights and improving reliability. I also optimized inference and retrieval pipelines for lower latency and 24/7 production stability.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
See more

Work Experience

Software Engineer - AI at HUMANITARIANS AI
June 1, 2025 - Present
Architected end-to-end vector data pipelines to ingest, transform and index millions of unstructured documents into Pinecone, reducing data retrieval and discovery latency by 65%. Engineered a RAG-based GenAI framework for Mycroft using LangChain and OpenAI API to enable source-grounded responses through optimized embedding, chunking and retrieval strategies. Developed agentic AI workflows for Madison to automate multi-step marketing intelligence using NLP-based agents and structured prompts, enabling scalable and consistent insight generation. Optimized inference and retrieval pipelines by implementing data observability, retry logic and performance tuning, reducing response latency by 40% while maintaining 24/7 production stability.
AWS Cloud Intern at ONEDATA SOFTWARE SOLUTIONS
September 1, 2024 - December 1, 2024
Designed data ingestion and transformation pipelines using AWS Glue and Python to support client analytics initiatives, processing 5M+ records per run and improving data readiness for downstream applications by 30%. Built and deployed ML infrastructure on AWS using ECS, Lambda, AWS Batch, and SageMaker to operationalize analytics and model workflows, reducing model deployment time from days to hours. Developed secure, low-latency data services using DynamoDB to support analytics-driven applications, achieving sub-100ms query latency while ensuring data integrity and high availability for enterprise use cases. Collaborated with senior engineers and client-facing teams to troubleshoot cloud performance and cost issues, contributing to ~20% cost optimization through rightsizing, service selection, and pipeline tuning.
Senior Software Engineer at INFOSYS
January 1, 2020 - May 1, 2022
Deployed scalable backend microservices using Node.js, Express, and exposing REST and GraphQL APIs that handled 150K+ daily requests and improved transaction response times by ~45%. Implemented data ingestion and ETL pipelines using Python and SQL, integrating relational databases and streaming systems to support real-time analytics and reporting. Optimized database performance across PostgreSQL through indexing, query optimization, and connection pooling, reducing query latency by ~35% and improving system throughput. Built CI/CD pipelines using Jenkins, Docker, and Kubernetes to support automated testing, containerized deployments, and zero-downtime releases, improving release reliability. Implemented production monitoring and observability using ELK stack and Grafana, reducing recurring production incidents by ~15% through proactive detection in an Agile environment.

Education

Master of Science in Information Systems at Northeastern University
January 11, 2030 - May 1, 2025

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet