RG

Backend / Platform / Applied AI Engineer

I build complete systems, not isolated demos.

I am Ritika Gupta. My portfolio is built around production-style systems: governed AI workflows, Go worker platforms, Kubernetes GitOps deployment, and cloud workspace control planes.

View ProjectsGitHubResume

System path

01Product workflow
02Backend services
03Workers / runtime
04Infra / GitOps
05Observability / evals

Each project exposes the path from product workflow to backend state, runtime execution, deployment, and proof through traces, evals, metrics, or screenshots.

About

I use projects as proof-of-work.

My learning path moved from frontend development into backend architecture, deployment, Go systems, DevOps/GitOps, cloud control planes, and applied AI workflows.

Each project is built to explore real production concerns: state, reliability, background processing, infrastructure, observability, evaluation, and human-in-the-loop workflows. The goal of this portfolio is to make those engineering decisions inspectable.

Backend architectureWorker systemsPostgres modelingRedis coordinationCloud runtime orchestrationKubernetes / GitOpsApplied AI workflow designRAG / agents / memory / evals

What I can offer

Engineering depth across backend, platform, and applied AI.

The portfolio is organized around three complete systems, each proving a different layer of engineering depth.

Ba

Backend systems

APIs, state machines, worker pipelines, Postgres models, Redis coordination, incidents, notification logs, and durable workflow state.

  • • Go and TypeScript backends
  • • Worker/event-driven systems
  • • Auth, RBAC, state modeling
Pl

Platform engineering

Dockerized local systems, Kubernetes manifests, GitOps workflows, External Secrets, ingress/TLS, Prometheus metrics, and autoscaling.

  • • Docker + Compose
  • • Kubernetes + ArgoCD
  • • Metrics + HPA
Ap

Applied AI workflows

RAG, agents, memory, human review, evals, traces, AI gateway logs, and deterministic controls around model behavior.

  • • Policy-grounded RAG
  • • Guarded tools
  • • Evals + observability

Proof of work

Featured systems

These projects are built as systems, not isolated demos. Start with ClaimFlow AI, then inspect RunState and SpinUp.

01 · Applied AI

ClaimFlow AI

Governed agentic AI workflow for motor-insurance claims.

ClaimFlow AI turns unstructured claim PDFs and emails into structured, policy-grounded, human-reviewed cases. It combines extraction, deterministic validation, clause-level policy RAG, guarded agent tools, workflow memory, evals, and run-level observability so the AI can assist without owning the final claim decision.

Applied AI systemsRAGAgentsMemoryHuman reviewEvalsObservability
Case StudyGitHubLive Product

02 · Backend / Platform

RunState

Production-style uptime monitoring platform with Go, Redis Streams, workers, Postgres, Docker, Kubernetes, and GitOps.

RunState monitors websites at regular intervals, records uptime and response-time history, detects status transitions, tracks incidents, persists notification logs, and exposes user/admin dashboards. The backend is built in Go with authentication, RBAC, Postgres persistence, Redis Streams, and a reusable worker engine. The deployment is managed through a separate GitOps repo with Kubernetes, ArgoCD, External Secrets, ingress/TLS, Prometheus, HPA, and image automation.

Go backendRedis StreamsWorkersPostgresIncident workflowsGitOpsKubernetes
Case StudyGitHubGitOps Repo

03 · Cloud Platform

SpinUp

Cloud workspace control plane for browser-based developer environments.

SpinUp turns a browser project creation request into a real EC2-backed code-server workspace. The backend control plane creates project metadata, tracks lifecycle state in Postgres, uses Redis for locks and runtime mirrors, allocates or reuses EC2 capacity from an Auto Scaling Group, waits for VM agent and container readiness, restores project files from S3, and exposes the workspace through a browser IDE.

Cloud control planesAWS EC2ASGRedis locksDockercode-serverS3 persistence
Case StudyGitHub

Engineering journals

Raw engineering trail behind the systems

These journals are positioned as proof-of-work: implementation decisions, debugging steps, architecture evolution, deployment work, and lessons learned.

Raw engineering journal

ClaimFlow AI Engineering Journal

Extraction to validation to RAG to agent to memory to evals to observability

Open journal →

Raw engineering journal

RunState Go Backend Journal

Go backend architecture, auth, RBAC, workers, Redis, Postgres, and APIs

Open journal →

Raw engineering journal

RunState DevOps Journal

Docker, Compose, CI, Kubernetes, GitOps, monitoring, and autoscaling

Open journal →

Raw engineering journal

DevOps Learning Lab

Docker, AWS, Kubernetes, Helm, GitOps, monitoring, and deployment practice

Open journal →

Resume

Target roles: Backend Engineer · Platform Engineer · Applied AI Engineer · AI Systems Engineer

A concise snapshot of my backend, platform, and applied AI experience across ClaimFlow AI, RunState, and SpinUp.

Download ResumeContactGitHub