Software Engineer
📋 The Short Version:
- Currently: Software Engineer at Oracle building Java REST APIs on OCI for enterprise SaaS
- Previously: Anguliyam (multi-agent systems, RAG), Adobe (React/TS), EPAM (data engineering)
- Core Focus: Multi-agent orchestration, enterprise retrieval systems, and production backend reliability
- Impact: 60%+ SQL response improvement, 70% lower manual processing, and 0%→91% test coverage growth
- Stack: Python, Java, TypeScript · AWS, GCP, OCI · FastAPI, Spring Boot, Next.js
What I Bring to the Table
Numbers from real work — not hypotheticals
What I Build
A quick look at what keeps me busy
About Me
The person behind the commits
Where I've Worked
Production code at 4 companies — here are the highlights
Software Engineer
Oracle
May 2025 – Present
- ▸Building Java REST APIs on OCI for enterprise SaaS clients in healthcare and finance with strict uptime/compliance requirements
- ▸Resolved a critical Oracle DB 23ai query bottleneck under concurrent load — execution plan analysis + index strategy drove 60%+ response-time improvement
- ▸Automated manual data-load workflow using Python on OCI, removing repeated weekly engineer intervention
- ▸Maintaining Jenkins CI/CD quality gates with JUnit coverage and consistent zero-rollback sprint delivery
Software Engineer — AI & Full-Stack Systems
Anguliyam
Jun 2024 – Apr 2025
- ▸Designed and deployed multi-agent orchestration systems with LangGraph and CrewAI, reducing manual processing by 70%
- ▸Built production RAG with hybrid retrieval (dense vector + keyword), improving answer relevance by 40% over baseline
- ▸Implemented human-in-the-loop governance with approval gates and audit logging for sensitive enterprise workflows
- ▸Integrated external tools, CRMs, and voice systems to trigger downstream actions beyond text-only responses
Software Engineer Intern
Adobe
Jan 2022 – Aug 2022
- ▸Built React and TypeScript UI components for Adobe Experience Cloud, focusing on accessible and consistent interfaces
- ▸Integrated Adobe Experience Platform APIs with graceful handling for partial data and API error states
- ▸Added Jest + React Testing Library coverage, catching a regression and increasing module coverage from 0% to 91%
- ▸Contributed to sprint design/code reviews and technical documentation in a 20+ engineer cross-functional setup
Software Engineer Intern
EPAM Systems
Dec 2020 – Mar 2021
- ▸Built Python and Java ETL modules with tests and documentation for client-facing data engineering workflows
- ▸Wrote SQL extraction/transformation/reporting queries powering downstream analytics and client financial reporting
- ▸Delivered sprint commitments in a global Agile team using JIRA, Git branching, and peer-reviewed code practices
GitHub Activity
Live commit activity and open source contributions
Commit Activity
ActiveReal-time commit activity over the past year
Real-Time Workflow Orchestration
Live visualization of production AI pipelines and distributed system workflows
LLM Processing
Vector Search
API Gateway
Frontend
Live Workflow: This visualization demonstrates real-time AI pipeline orchestration—from LLM processing and vector search to API gateway and frontend delivery. Each step shows actual metrics and processing states, reflecting production system behavior with fault tolerance, monitoring, and scalable architecture.
System Design
Architecture, scalability, and distributed systems expertise
SmartBuy AI: Production E-Commerce Platform with AI Integration
A scalable full-stack eCommerce platform with AI-powered navigation, real-time inventory management, and optimized performance.
Architecture Overview
- •Frontend: Next.js (SSR/SSG) with React, deployed on Vercel Edge Network for global CDN distribution
- •Backend: FastAPI microservices with async/await for scalable request handling
- •Database: PostgreSQL with connection pooling, fact/dimension tables for analytics, Redis cache layer (95% hit rate)
- •Data Pipelines: Python + SQL ETL workflows with Airflow orchestration, data quality checks, and analytics-ready schemas
- •AI Service: OpenAI API with request batching, response caching, and fallback mechanisms
- •Vector Search: Pinecone for semantic product search with 50K+ product embeddings
Scalability & Performance
- •Load Handling: Scalable architecture with horizontal scaling, connection pooling, and caching strategies
- •Response Times: API latency <300ms (p95), AI queries <2s, page loads <1.2s
- •Caching Strategy: Multi-layer (CDN, Redis, in-memory) reducing DB load by 80%
- •Database: Read replicas for scaling, connection pooling (max 100 connections), query optimization
- •Monitoring: Real-time metrics (Prometheus), error tracking (Sentry), APM (New Relic)
Key Design Decisions & Trade-offs
1. Microservices vs Monolith
Chose FastAPI microservices for independent scaling of AI service vs. core eCommerce logic, accepting added complexity for better resource utilization.
2. Vector DB Selection
Pinecone over self-hosted (FAISS/Milvus) for managed scalability and lower ops overhead, trading cost for reliability.
3. Caching Strategy
Multi-layer caching (CDN → Redis → DB) prioritized read performance, accepting eventual consistency for product data.
4. Failure Handling
Circuit breakers for AI API, graceful degradation to keyword search, retry logic with exponential backoff for improved reliability during service outages.
Scaling Strategy
Horizontal Scaling
FastAPI instances behind load balancer, auto-scaling based on CPU/memory (2-10 instances), stateless design for easy scaling.
Database Scaling
Read replicas for query distribution, connection pooling, query optimization, and planned sharding for 100K+ products.
Cost Optimization
AI request batching, response caching (60% cache hit rate), CDN for static assets, reducing infrastructure costs by 40%.
Why Work With Me
Here's what I think sets me apart
I Ship Real Products
I build complete systems, not isolated demos: HealthScan (agentic healthcare assistant), SmartBuy v2 (multimodal shopping agent), Blinds & Boundaries (AI try-on), and AI Resume Tailor (application workflow automation).
I Fix What's Broken
At Oracle: fixed API failures (87%→98%), optimized a 6-second query to 2 seconds. At Adobe: found a Redux race condition nobody else could trace. I debug production issues with patience and precision.
I Learn Fast & Go Deep
I work across Java, Python, and TypeScript based on system needs. That range lets me move from DB performance debugging and CI/CD to agent orchestration and production UI delivery without handoff bottlenecks.
Projects
Selected shipped projects with production-grade architecture
SmartBuy v2 — Multimodal AI Shopping Agent
A real multimodal shopping agent with persistent WebSocket connectivity to Gemini Multimodal Live API for simultaneous voice, webcam context, and two-way interaction.
ScanX (HealthScan) — AI Healthcare Assistant
Agentic AI healthcare assistant with a 3-engine architecture for prescription extraction, action planning, and browser automation with interaction safety checks.
AI Resume Tailor — Full-Stack Job Application Platform
A Vercel-only Next.js App Router platform that parses job descriptions with Claude AI, tailors resume DOCX output via XML manipulation, and logs applications to Google Sheets.
Blinds & Boundaries — AI Virtual Try-On Platform
Virtual try-on application for window blinds using computer vision and 3D rendering. Enables customers to visualize products in their actual space with realistic lighting and perspective. Deployed on Azure with real-time image processing.
Railway Predictive Maintenance System
Real-time predictive maintenance system for railway equipment using machine learning. Processes sensor data streams with TensorFlow LSTM models to predict equipment failures, enabling proactive maintenance and reducing downtime.
Let's Work Together
I'm always open to interesting conversations — whether it's about a role, a collaboration, or just a cool technical problem. Let's chat.
Get In Touch
I'd love to hear from you! Let's discuss your next project.
Or email me directly at laharikarrothu@gmail.com
What I'm Currently Into
- • Building AI agents that can actually do useful things (not just chatbots)
- • Distributed systems design — event-driven architecture, message queues
- • Healthcare tech — making HL7/FHIR less painful for everyone
- • Open source contributions — looking for interesting projects to contribute to
Case Study: SmartBuy AI
How I shipped an AI shopping assistant end-to-end
Overview
SmartBuy AI embeds a conversational assistant inside a full-stack eCommerce experience. It handles search, recommendations, and navigation with a lightweight vector index and FastAPI services.
Problem
Users struggled to find products quickly and dropped off after slow search or poor recommendations.
Solution
Conversational assistant + semantic search backed by FastAPI, embeddings, and cached intents for sub-3s responses.
Tech Stack
Next.js, TypeScript, FastAPI, PostgreSQL, OpenAI API, Tailwind, Vercel
My Role
Architecture, API design, AI integration, frontend UX, deployment.
Results
- • AI query responses in <3s with cached intents
- • Faster product discovery via semantic search and voice/text navigation
- • Production-ready deployment with monitoring and uptime focus
Architecture (high level)
Architecture: ScanX Agent Loop
Tech Stack
Tools I actually use — not just list on a resume
Technical Expertise
Technologies and tools I work with
🧩Full-Stack & Backend
🤖AI / ML & Agents
📡Data Engineering & Pipelines
☁️Cloud & Infrastructure
Education
Academic background in Computer Science
Master of Science in Computer Science
Florida Institute of Technology
Aug 2022 – May 2024
GPA: 3.6/4.0
Bachelor of Science in Computer Science
KL University
2022
GPA: 3.8/4.0
Certifications & Badges
Professional certifications and verified achievements
I Write Too
Thoughts on AI, distributed systems, and what I'm learning
How I Think About Engineering
Deep dives into the problems I've solved and the trade-offs I've made
Scaling FastAPI for High-Throughput AI Workloads
How I optimized FastAPI microservices for scalable request handling, implementing connection pooling, async/await patterns, and request batching for AI API calls.
Vector Database Optimization for Semantic Search
Deep dive into optimizing Pinecone vector search for 50K+ product embeddings, achieving 99.5% retrieval accuracy with <500ms query time through embedding compression and indexing strategies.
Building Fault-Tolerant LLM Pipelines
Designing resilient AI workflows with circuit breakers, graceful degradation, retry logic, and fallback mechanisms for improved reliability during AI service outages.
Multi-Layer Caching Strategy for E-Commerce
Implementing CDN → Redis → Database caching layers, achieving 95% cache hit rate and reducing database load by 80% while maintaining data consistency.
Real-Time Monitoring for Production AI Systems
Building comprehensive monitoring with Prometheus, Sentry, and custom metrics for LLM pipelines, enabling real-time alerting and performance tracking with <100ms overhead.
ETL Pipeline Design for Analytics at Scale
Architecting Python + SQL ETL pipelines processing 1,000+ structured records/day with data quality checks, fact/dimension table design, and Airflow orchestration, improving query performance by 35% and reducing data issues by 40%.