HELLO_WORLD.exe / KUSHAL_JAIN
Building
Intelligence
at Scale.
7+ years engineering cloud-native backend systems. Now at the frontier — building AI platforms with RAG pipelines, LLM orchestration, and vector search that power real enterprise intelligence.
Engineering at the
AI frontier
I'm a Senior Software Engineer based in Orange County, CA with 7+ years building cloud-native backend systems. At Slalom, I design and deliver enterprise-grade architectures that scale — and increasingly, that means putting AI at the core.
My current focus is AI-enabled platforms: multi-tenant knowledge systems with RAG pipelines, vector search over large document corpora, prompt engineering for grounded responses, and the observability + cost controls that make LLM systems production-safe.
I hold five cloud certifications — AWS Solutions Architect, AWS Developer, AWS AI Practitioner, AWS Cloud Practitioner, and HashiCorp Terraform Associate. Cloud-agnostic by practice: I design and ship on AWS, GCP, Azure, and Firebase, applying the same engineering rigor across platforms — reliability, observability, pragmatic design.
const engineer = {
name: "Kushal Jain",
role: "Sr. Software Engineer",
focus: [
"AI Platform Engineering",
"RAG Systems",
"Cloud-Native Backend",
],
certs: ["AWS SAA", "AWS AI-P", "TF-003"],
ms: "CS Eng, CSU Fullerton"
}
› ▌
Tools I wield
with precision
AI & LLM SYSTEMS
CLOUD & INFRASTRUCTURE
BACKEND & PLATFORM
Where I've
shipped things
Senior Software Engineer
Designing and delivering cloud-native backend and platform architectures for enterprise clients. Building AI-enabled backend services including document ingestion pipelines, metadata processing, and search-oriented systems supporting LLM workflows.
- ›Built multi-tenant AI knowledge platforms with RAG pipelines on AWS
- ›Implemented CI/CD pipelines and infrastructure automation with Terraform
- ›Owned architecture reviews and production readiness for core services
- ›Delivered scalable backend solutions translating complex business requirements
Things I've
built & shipped
Enterprise AI Knowledge Assistant
Multi-tenant enterprise AI knowledge platform powered by Retrieval-Augmented Generation. Built secure document ingestion, text chunking, embeddings generation, and vector search pipelines on AWS — with full tenant isolation and AI cost governance.
- ›Multi-tenant architecture with strict data isolation per tenant
- ›Vector search over document embeddings using AWS OpenSearch
- ›Usage limits, rate limiting, and cost controls for LLM workloads
- ›Terraform-managed infrastructure with automated CI/CD deployment
AI Developer Productivity Platform
AI-assisted developer productivity platform providing code understanding, architecture explanations, and contextual Q&A over large codebases. Integrated into CI/CD for automated code review insights.
- ›RAG pipelines over source code, docs, and architecture diagrams
- ›Context window optimization and prompt versioning for grounded responses
- ›CI/CD integration for automated code review and architectural feedback
- ›Observability and cost governance for LLM usage at scale
Real-Time 3D Virtual Tradeshow Platform
Cloud-hosted real-time 3D virtual interaction platform enabling audio/video communication and immersive user experiences in first-person and third-person views.
- ›Unity game engine with AWS pixel-streaming for cloud rendering
- ›WebRTC-based audio/video chat in 3D virtual environments
- ›End-to-end ownership from architecture to production deployment
- ›Impressed enterprise clients and trade exhibition stakeholders
Let's build
something
together.
I'm open to senior engineering roles, AI platform opportunities, and consulting engagements — especially where LLMs meet production systems. Based in Orange County, CA. Open to remote across the USA.