§ Work
Systems I’ve built
Production systems. All metrics are real.
Gerber/BOM Intelligence Extraction Engine
Problem
Manual review of PCB manufacturing files was a bottleneck at 150+ uploads per day. Engineers were spending hours on structured data extraction that could be automated.
Approach
Built an async Java pipeline using Spring Batch — OCR extraction, structured normalization, validation rules, and S3-backed storage. Zero manual review for standard file formats.
Outcome
150+ PCB files auto-processed daily
Production RAG Assistant with Agentic Tool-Calling
Problem
Support team fielding repetitive engineering queries. High escalation rate creating load on senior engineers.
Approach
LangChain4j RAG pipeline with vector store retrieval and agentic tool-calling. Answers grounded in internal documentation with fallback to human escalation.
Outcome
40% reduction in support escalations
Event-Driven Architecture Migration
Problem
Monolithic deployment pipeline causing 2-hour deployment windows. Tight service coupling blocking independent team velocity.
Approach
Migrated to Kafka Streams with Schema Registry for event-driven service communication. GitHub Actions CI/CD pipeline built from scratch alongside the migration.
Outcome
Deploy time: 2 hours → 12 minutes
Technologies I specialize in
Core Backend
Messaging
Cloud · AWS
AI · LLM
Data
Observability
DevOps
My Story
I'm a backend engineer who's spent 9 years building the systems that don't get the glory — the pipelines that process 150+ documents a day, the Kafka topology that decouples services so deployments go from 2 hours to 12 minutes, the RAG assistant that quietly cut support load by 40%. I'm the person on the team who figures out how to make the AI actually work in production.
Deep expertise in Kafka, AWS (Lambda, ECS, DynamoDB), and modern AI/LLM patterns. Recent wins: migrating to event-driven architecture with Kafka Streams, optimizing deployment time from 2 hours to 12 minutes via GitHub Actions, instrumenting microservices with OpenTelemetry for full distributed tracing.
I write about system design, Kafka, and LangChain4j on this blog — deep technical posts because all my production work is proprietary, and writing is how I show the depth.
Outside of code: studying for the Confluent Kafka Streams certification, exploring new Claude models and LLM capabilities, and always happy to talk distributed systems.
Areas of Expertise
RAG & LangChain4j
Document ingestion, chunking, vector stores, agentic tool-calling, prompt engineering
Kafka & Event Streaming
Kafka Streams, Kafka Connect, Schema Registry, real-time aggregations, event-driven microservices
Java & Spring Boot
Spring Boot 3, Spring Data, Spring Batch, reactive streams, performance tuning
AWS Architecture
Lambda, ECS, S3, DynamoDB, API Gateway, Terraform, deployment automation
System Design
Microservices, distributed tracing (OpenTelemetry), event-driven patterns, scalability
DevOps & Observability
GitHub Actions CI/CD, Docker, Kubernetes, Prometheus, Grafana, CloudWatch
Get in Touch
Senior Java + AI engineer writing about Kafka, RAG, and system design. Reach out or grab the resume.