Hi, I'm Giridhar 👋
I'm a Software Engineer
Software Engineer with 3+ years building scalable microservices and RESTful APIs for enterprise fintech at PayPal and J.P. Morgan. I ship reliable 0-to-1 backend systems and AI/LLM-powered automation that reduce manual effort and improve performance. AWS Certified Solutions Architect.
About Me
Software Engineer with 3+ years building scalable microservices and RESTful APIs for enterprise fintech at PayPal and J.P. Morgan. Focused on shipping reliable 0-to-1 backend systems and AI/LLM-powered automation that reduce manual effort and improve performance.
AWS Certified Solutions Architect skilled in Java, Spring Boot, Python, distributed systems, and system design. Experienced building secure, high-throughput services, integrating LLM APIs, and delivering production-ready solutions across cloud-native environments in Agile teams.
Backend Expertise
- • Java, Spring Boot & Python
- • RESTful Microservices
- • Distributed Systems & System Design
- • AI/LLM Automation
Cloud & DevOps
- • AWS (Certified Solutions Architect)
- • Docker & Kubernetes
- • Kafka & Event-Driven Architecture
- • CI/CD & Agile Development
Education
M.S. Computer Science
Lamar University
Beaumont, TX · GPA: 4.0
Relevant Coursework: Data Structures & Algorithms, Operating Systems, Distributed Systems, Database Systems, Computer Networks
Awards & Certifications
- Outstanding Graduate Student Award — Lamar University (May 2025). Awarded for academic excellence (4.0 GPA) and graduate teaching assistantship contributions.
- AWS Certified Solutions Architect – Associate (Jul 2023).
Work Experience
Software Engineer
PayPal
Python, AWS, MCP, Agentic AI, Microservices
- Engineered scalable backend services using Python and AWS for regulatory compliance systems, reducing maintenance effort by 40% and improving service reliability.
- Led design and delivery of reusable Python and AWS backend service libraries for PayPal/Venmo, adopted across 5 product teams and validated through comprehensive unit and integration testing.
- Built and deployed Model Context Protocol (MCP) servers powering end-to-end agentic AI workflows, automating manual engineering tasks and eliminating approximately 10 hours/week of repetitive work.
- Developed a self-service merchant auto-withdrawal configuration tool for Account Managers and Sales, slashing request turnaround from approximately 6 hours to under 1 minute.
- Delivered a self-service utility for the CSM team on PayPal Automatic Transfers, reducing inbound queries to the Product Development team by 80%.
Software Engineer
J.P. Morgan
Java, Spring Boot, Kafka, LLM APIs, Cloud Migration
- Architected middleware for the Asset Management Sales Experience Platform, creating a single authoritative database for 1M+ annual sales, lead, and client records across integrated enterprise applications.
- Integrated LLM APIs to automate client-conversation transcription and activity logging, saving advisors 300+ hours annually and improving post-interaction efficiency.
- Engineered secure Spring Boot microservices processing 2M+ Kafka events/day with end-to-end cryptography, and led on-premises to cloud data migration (authored a published white paper).
- Won 2nd place among 100+ teams at the 2022 JPMC Global Hackathon and 2nd among 90+ teams in 2021 for engineering innovation.
Technical Skills
Featured Projects
- Architected a microservices-based analytics platform with decoupled FastAPI REST services and background workers, using Redis queues for asynchronous job processing and MongoDB for persistent analytics, enabling horizontal scalability and fault isolation.
- Containerized the full stack (API, worker, Redis, MongoDB) with Docker and Docker Compose, adding service health checks for reproducible, one-command deployments.
- Engineered an end-to-end NLP/ML pipeline ingesting YouTube comments with embeddings, UMAP dimensionality reduction, HDBSCAN clustering, and RAPTOR-style hierarchical summarization for fast, context-aware insight retrieval.
- Architected a multi-agent NL-to-SQL system (RAG + LLMs) converting natural language into executable SQL via a query-enhancement, schema-retrieval, table-selection, column-pruning, and generation pipeline.
- Fine-tuned a BERT classifier (90% recall) over a vector-retrieval layer for table selection, reducing latency from 18s (GPU) to 0.28s (CPU) while improving accuracy.
- Designed and built a high-throughput URL shortening service handling 10K+ requests/minute using Spring Boot, with Redis caching reducing redirect latency to sub-5ms and MySQL for persistent storage.
- Implemented consistent hashing for distributed key generation across multiple service instances, ensuring zero collisions and horizontal scalability behind an Nginx load balancer.
- Containerized the full stack with Docker Compose (API server, Redis, MySQL, Nginx) and deployed with health checks, achieving 99.9% uptime under sustained load testing with JMeter.
- Architected a multi-agent AI diagnostic system using GPT-4o and Python, leveraging multithreading to process patient data 15% faster across 5 specialized medical analysis agents.
- Optimized inter-agent communication and data processing pipelines, reducing end-to-end diagnostic response time by 30% for real-time clinical analysis.
- Deployed with Kubernetes orchestration and automated CI/CD pipelines, reducing deployment errors by 60% and enabling 2x faster release cycles.
- Designed and deployed a cloud-native image classification service on AWS, processing 100+ concurrent requests using SQS message queuing and auto-scaling EC2 instances running a pre-trained deep learning model.
- Built a Node.js web tier handling image uploads and async job tracking, with Python-based inference workers consuming from SQS and storing results in S3, achieving sub-3 second end-to-end processing time.
- Implemented auto-scaling policies using CloudWatch metrics, dynamically spinning up EC2 instances under load and scaling down to zero during idle, reducing compute costs by 60%.
My Blogs
Sharing insights, experiences, and knowledge about technology, AI, and life.
Building Multi-Agent AI Systems: Lessons Learned
Exploring the challenges and breakthroughs in building a RAG-powered multi-agent NL2SQL pipeline that turns natural language into executable SQL.
My Journey from India to US: A Software Engineer's Perspective
Sharing my experience of transitioning from working in India to pursuing a Master's degree in the US and the lessons learned along the way.
Processing 2M+ Kafka Events a Day: Scaling Event-Driven Microservices
How I engineered secure, high-throughput Spring Boot microservices at J.P. Morgan and the trade-offs of event-driven architecture at scale.
Graduate School in the US: Tips for International Students
Essential advice for international students pursuing Computer Science graduate programs in the US, from applications to campus life.
Automating Engineering Workflows with MCP Servers and Agentic AI
How I built Model Context Protocol servers powering end-to-end agentic AI workflows that eliminated ~10 hours/week of repetitive engineering work.
Get In Touch
I'm always interested in new opportunities and collaborations. Let's connect and discuss how we can work together!
giridharswe12@gmail.com
Phone
(409) 219-4463
Location
Austin, TX
Ready to collaborate?
I'm currently open to new opportunities and exciting projects. Let's discuss how we can work together to create something amazing!
Send Message