Cloud  /  DevOps  /  AI · FDE
Jithendra
Kantharaju

AI Engineer with nearly three years of DevOps experience — built and deployed LLM agents, RAG pipelines, and AIOps tooling on AWS EKS end-to-end. Currently finishing an MS at USF and certified across AWS, GCP, Azure, OCI, Anthropic, and Redis.

3+
Years Production Experience
40%
Fewer Deploy Errors
60%
Faster Incident Resolution
10
Cloud Certifications
Get In Touch↗
Scroll
About

Who I Am

I'm an AI Engineer and Forward Deployed Engineer who builds production-grade AI systems — LLM agents, RAG pipelines, and AIOps tooling that run reliably on AWS EKS. My background spans nearly three years of DevOps engineering in India and the United States, where I've shipped infrastructure for teams of 10,000+ users.

I specialize in closing the gap between ML research and production reality — writing the Terraform, Helm charts, GitHub Actions pipelines, and observability stacks that keep AI systems running at scale. Currently finishing my MS in Computer Engineering at the University of South Florida.

🎓
Education
MS Computer Engineering, University of South Florida
📍
Location
United States
💼
Current
AI Systems Engineer @ Face Friends Foundation
🤖
Focus
LLM Agents · RAG Pipelines · AIOps · EKS
🏆
Certs
10 Cloud + AI Certifications
📧
Email
jithendra.kantharaju@gmail.com
Experience & Education

The Journey

Work Experience
AI Systems Engineer
Face Friends Foundation · United States
CurrentSep 2026 – Present
  • ›Architecting AI-powered fundraising workflows across Symphony, Bitrix24, and Wix platforms
  • ›Publishing weekly intelligence briefs synthesizing AI and nonprofit sector developments
  • ›Producing volunteer training documentation to accelerate team onboarding
AI WorkflowsSymphonyBitrix24WixLLMAutomation
Technical Operations Analyst
Compass Group USA · United States
Aug 2025 – May 2026
  • ›Maintained 99.9% POS system uptime across 10,000+ user environments
  • ›Reduced incident frequency by 25% through proactive monitoring and runbook automation
  • ›Authored operational runbooks that standardized incident response procedures
POS SystemsIncident ManagementRunbooksMonitoringSLA
DevOps Engineer
Corezeal Technologies · India
Mar 2022 – Dec 2024
  • ›Reduced manual infrastructure operations ~70% using Terraform and Ansible across 4 environments
  • ›Cut deployment time 40% via GitHub Actions and GitLab CI pipelines with ArgoCD GitOps
  • ›Secured the pipeline end-to-end: HashiCorp Vault secrets injection, Trivy image scanning, OPA policy gates
  • ›Implemented Prometheus + Grafana + ELK observability stack for production workloads on EKS
TerraformAnsibleKubernetesArgoCDHashiCorp VaultTrivyAWS EKSGitHub Actions
Engineering Intern
Agimus Technologies Pvt Ltd. · India
Sep 2021 – Oct 2021
  • ›Built a Python-based IoT healthcare monitoring platform delivering patient alerts under 30 seconds
  • ›Integrated sensor data pipelines with real-time alerting for critical patient vitals
PythonIoTHealthcareReal-time Alerting
Education
MS Computer Engineering
University of South Florida · United States
2024 – Present
  • ›Graduate coursework in Machine Learning, Distributed Systems, and Cloud Computing
MLDistributed SystemsCloud
BE Electronics & Communication
Siddaganga Institute of Technology · India
2017 – 2021
  • ›Bachelor of Engineering with focus on embedded systems and signal processing
Embedded SystemsSignal Processing
Technical Arsenal

Skills

AIOps & ML
8 tools & technologies
LangGraphAWS BedrockRAG / LLMFastAPIChromaDBOpenAILangChainAnthropic Claude
All categories
Certifications

Credentials

10 active certifications across Anthropic, AWS, GCP, Azure, OCI & Redis

Claude Certified Architect
Anthropic
Claude Certified Architect
2026
Solutions Architect Associate
AWS
Solutions Architect Associate
2026
AWS AI Practitioner
AWS
AWS AI Practitioner
2026
AWS Cloud Practitioner
AWS
AWS Cloud Practitioner
2026
Associate Cloud Engineer
Google Cloud
Associate Cloud Engineer
2026
Azure Fundamentals
Microsoft Azure
Azure Fundamentals
2025
OCI DevOps Professional
Oracle Cloud
OCI DevOps Professional
2025
OCI Foundations Associate
Oracle Cloud
OCI Foundations Associate
2025
OCI AI Foundations
Oracle Cloud
OCI AI Foundations
2025
Redis Certified Developer
Redis
Redis Certified Developer
2026
AnthropicAWSGoogle CloudMicrosoft AzureOracle CloudRedis
Work

Projects

Production systems — not demos. Real problems, real stacks, measured outcomes.

🤖
EKS 1.34TerraformGitHub Actions
Enterprise CloudOps AI Platform
01 / 05
🔒
GitHub ActionsArgoCDHashiCorp Vault
DevSecOps Reference Infrastructure
02 / 05
⚙
GitHub ActionsGitOpsTerraform
GitOps CI/CD Pipeline on AWS EKS
03 / 05
🎬
JenkinsDockerEKS
Multi-Tier Cloud App on AWS
04 / 05
🎤
PythonScikit-learnSVM
Detecting Voice Clones in Assistants
05 / 05
Problem: Incident triage took 60+ minutes; teams lacked a live view of EKS health, CloudWatch alerts, and Prometheus metrics simultaneously.
EKS 1.34TerraformGitHub ActionsArgoCDAWS BedrockFastAPIChromaDBKustomizePrometheus

Enterprise CloudOps AI Platform

Deployed 8 microservices (React, Node.js/TypeScript gateway, 5 Python backends, PostgreSQL) to live EKS 1.34 via modular Terraform. GitHub Actions builds all 8 images in parallel with matrix builds, rewrites Kustomize tags, and ArgoCD self-heals on drift.

✓Built "Kira" — AWS Bedrock Agent (Nova Lite) with 3 Lambda tools that auto-diagnoses incidents
✓RAG assistant (FastAPI + ChromaDB + OpenAI) with on-topic prompt guardrails on the same cluster
↗ View on GitHub
Contact

Get In Touch

Whether it's a role, a project, or just a question about the stack — I read every message and I'm quick to respond.

Open to opportunities

Actively looking for AI Engineer, MLOps, or FDE roles starting 2026.

send_message.sh