Senior Software Engineer · Backend, Cloud & AI-Integrated Systems
Go · AWS · Kubernetes · React · Production AI
I'm a Senior Software Engineer building production-grade backend platforms with a strong focus on:
- High-throughput APIs
- Cloud-native infrastructure
- Safe, observable AI integrations
My recent work centers on integrating LLMs into real backend workflows — not demos — with attention to cost control, reliability, evaluation, and failure modes.
| Project | Contribution | Status |
|---|---|---|
| go-chi/chi | Fix: Prevent double handler invocation in RouteHeaders middleware | ✅ Merged |
| gin-gonic/gin | Fix: Typos, documentation clarity, and dead code removal | ✅ Merged (v1.12) |
- Clear service boundaries & ownership
- Errors that explain themselves (and stop in the right place)
- Observability as a first-class feature
- AI systems that are auditable, testable, and bounded
- Shipping value without turning systems into research projects
I work on practical AI integrations, not generic prompt experiments.
What that means in practice:
- LLM-powered document & image processing pipelines
- Prompt versioning and deterministic execution where possible
- Guardrails, fallbacks, and timeouts around model calls
- Async processing, retries, and webhook-driven workflows
- Cost-aware design (batching, sampling, selective invocation)
- Human-in-the-loop & golden-task validation strategies
Current / Recent Focus Areas:
- LLM-assisted data extraction & classification
- AI quality monitoring using golden datasets
- Backend orchestration around Gemini / OpenAI-style models
- Safely embedding AI into existing Go services
- Open source contributor to Chi and Gin — two of Go's most popular HTTP frameworks
- Backend platforms processing large-scale PDF & image workflows
- AI-assisted pipelines with human validation & quality metrics
- Performance & payout monitoring systems using real-time data
- Internal developer platforms focused on reliability and clarity
(Selected projects are shared in individual repositories)
I write about:
- Error handling & service boundaries in Go
- Structuring long-lived backend systems
- Cloud & Kubernetes without unnecessary complexity
- Lessons from integrating AI into production backends
- AI evaluation frameworks for backend teams
- LLM observability & drift detection
- Platform engineering for AI-heavy services
- Cost-efficient AI usage patterns in cloud-native systems
If you care about:
- Backend engineering done right
- AI in production (not hype)
- Go, cloud platforms, and system design
Let's talk 👋
"AI is just another dependency — treat it like one."